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

    Neuronpedia

    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. 14106
    Prev
    Next
    INDEX
    Explanations

    phrases related to law enforcement, criminal charges, and violent acts

    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
    +0.09
    0.6%
    752
    +0.09
    0.6%
    235
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    154
    +0.09
    0.12
    151
    +0.09
    0.15
    253
    +0.06
    0.11
    Negative Logits
    soDeliveryDate
    -0.65
    markets
    -0.49
    ocobo
    -0.47
    shr
    -0.47
    bank
    -0.45
    mite
    -0.45
    ift
    -0.45
    izen
    -0.45
     sands
    -0.45
    iesel
    -0.44
    POSITIVE LOGITS
     aggravated
    0.56
     punishable
    0.56
     indecent
    0.54
     manslaughter
    0.51
     wounding
    0.51
     captcha
    0.49
     blasphemy
    0.48
     trespass
    0.47
     stalking
    0.46
    against
    0.46
    Activations Density 7.631%

    No Known Activations