© 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 EvalsExportsinterp-engineNEWAPI 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. 32421
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal issues and 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
    447
    +0.18
    0.8%
    360
    +0.11
    0.5%
    475
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.18
    0.18
    608
    +0.11
    0.26
    455
    +0.11
    0.24
    Negative Logits
     Manifest
    -0.69
     Unic
    -0.68
     Communities
    -0.67
    roid
    -0.65
     Capital
    -0.63
     Measures
    -0.63
     Approach
    -0.62
     transforms
    -0.61
     Zy
    -0.60
    ashing
    -0.60
    POSITIVE LOGITS
     now
    1.08
    now
    0.92
    raf
    0.81
     NOW
    0.80
    psey
    0.79
     hindsight
    0.78
    bol
    0.77
    Fast
    0.76
    çĶ°
    0.75
    externalActionCode
    0.73
    Activations Density 24.919%

    No Known Activations