© 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. 33731
    Prev
    Next
    INDEX
    Explanations

    legal and criminal terms, specifically related to criminal activities

    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
    324
    +0.11
    0.6%
    158
    +0.09
    0.5%
    591
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.23
    711
    +0.09
    0.06
    324
    +0.08
    0.10
    Negative Logits
    assies
    -0.71
    tics
    -0.62
    ells
    -0.61
    esters
    -0.60
     Keys
    -0.60
     Scouts
    -0.58
     Machines
    -0.57
    steps
    -0.57
     Agric
    -0.56
     Gems
    -0.56
    POSITIVE LOGITS
    ccording
    0.71
    è¦ļéĨĴ
    0.61
     estimate
    0.60
     ranging
    0.60
     standpoint
    0.60
     consisting
    0.60
     exceeding
    0.59
     spokeswoman
    0.59
     coefficient
    0.58
     spokesperson
    0.58
    Activations Density 7.827%

    No Known Activations