© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 33692
    Prev
    Next
    INDEX
    Explanations

    phrases related to law enforcement agencies and illegal activities such as drug trafficking, enforcement operations, and legal actions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    119
    +0.07
    0.5%
    183
    +0.07
    0.5%
    360
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.07
    0.18
    709
    +0.07
    0.10
    326
    +0.07
    0.19
    Negative Logits
    entary
    -0.56
    izations
    -0.53
    ommod
    -0.51
    ifications
    -0.50
    atters
    -0.49
    asters
    -0.48
    aughtered
    -0.47
    hester
    -0.47
    nesia
    -0.45
    rum
    -0.44
    POSITIVE LOGITS
     Enforcement
    0.57
     poaching
    0.51
     agent
    0.51
     raiding
    0.50
     agents
    0.50
     narcotics
    0.49
     DEA
    0.48
    SPONSORED
    0.48
     seizure
    0.47
     forfeiture
    0.47
    Activations Density 6.285%

    No Known Activations