© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 3652
    Prev
    Next
    INDEX
    Explanations

    terms related to legal issues and government controversy

    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
    132
    +0.10
    0.6%
    247
    +0.07
    0.5%
    2
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.25
    132
    +0.07
    0.11
    247
    +0.06
    0.09
    Negative Logits
    netflix
    -0.52
    yond
    -0.49
    background
    -0.49
    ect
    -0.48
    CLOSE
    -0.45
     chrom
    -0.45
    chrom
    -0.44
     unreal
    -0.42
    mac
    -0.42
     unreasonable
    -0.41
    POSITIVE LOGITS
     Flavoring
    0.48
    ij士
    0.47
    heid
    0.47
    elist
    0.46
     Honour
    0.46
    naire
    0.46
    xual
    0.44
     Programme
    0.44
     Pact
    0.44
    riors
    0.44
    Activations Density 8.066%

    No Known Activations