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. 45107
    Prev
    Next
    INDEX
    Explanations

    text related to news and discussions about various television episodes

    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%
    74
    +0.06
    0.4%
    498
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.09
    0.29
    393
    +0.06
    0.32
    74
    +0.06
    0.11
    Negative Logits
    lihood
    -0.44
    enting
    -0.42
    itarian
    -0.41
    quartered
    -0.40
    kie
    -0.40
     beverage
    -0.40
    fortable
    -0.40
     therm
    -0.39
    coni
    -0.38
    enic
    -0.38
    POSITIVE LOGITS
     onwards
    0.55
    XXX
    0.48
    isode
    0.46
    ilogy
    0.46
     rewritten
    0.43
     installments
    0.43
    ãĥ¯ãĥ³
    0.43
     Awakens
    0.42
     finale
    0.42
     sequels
    0.42
    Activations Density 15.953%

    No Known Activations