© 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. 4934
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software and hardware vulnerabilities in devices

    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
    +0.16
    0.7%
    68
    +0.13
    0.6%
    332
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.33
    326
    +0.13
    0.28
    575
    +0.12
    0.19
    Negative Logits
    orate
    -0.76
    arding
    -0.76
    oard
    -0.72
    naissance
    -0.72
    iard
    -0.71
    arded
    -0.69
    urate
    -0.69
    uate
    -0.69
     secrecy
    -0.69
    ulhu
    -0.68
    POSITIVE LOGITS
    ustain
    0.86
    plings
    0.86
    rano
    0.78
    atchewan
    0.78
     Rough
    0.75
    atoon
    0.74
    ORTS
    0.74
    ificant
    0.72
    earcher
    0.72
     Snape
    0.71
    Activations Density 11.653%

    No Known Activations