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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 45743
    Prev
    Next
    INDEX
    Explanations

    words related to financial transactions and legal disputes

    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
    373
    +0.13
    0.7%
    447
    +0.12
    0.7%
    481
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    639
    +0.13
    0.12
    709
    +0.12
    0.13
    288
    +0.11
    0.21
    Negative Logits
     Barrier
    -0.74
    agall
    -0.60
    wcs
    -0.60
    tube
    -0.58
     insulated
    -0.57
     hypers
    -0.56
    zai
    -0.56
    schild
    -0.55
     skelet
    -0.55
     Greenwich
    -0.54
    POSITIVE LOGITS
    lled
    0.72
    arious
    0.71
    enance
    0.70
    ings
    0.68
     bribes
    0.64
    tons
    0.63
    ieri
    0.61
    xual
    0.61
     duties
    0.60
    neau
    0.59
    Activations Density 7.520%

    No Known Activations