Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 45173
    Prev
    Next
    INDEX
    Explanations

    words related to legal and ethical issues around relationships and marriage

    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
    651
    +0.12
    0.5%
    641
    +0.12
    0.5%
    218
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.12
    0.09
    582
    +0.12
    0.05
    302
    +0.12
    0.09
    Negative Logits
     Carib
    -0.80
     Yankee
    -0.77
    \<
    -0.75
     indifference
    -0.74
     predic
    -0.72
    ãĥł
    -0.71
     populous
    -0.70
    isted
    -0.68
     Dangerous
    -0.68
     Ambrose
    -0.68
    POSITIVE LOGITS
    ming
    1.50
    irez
    1.50
    mers
    1.36
    pton
    1.36
    matical
    1.32
    bler
    1.26
    atic
    1.25
    med
    1.24
    bling
    1.23
    blers
    1.21
    Activations Density 5.413%

    No Known Activations