© 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
    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. 33021
    Prev
    Next
    INDEX
    Explanations

    terms related to linguistic modal verbs and accompanying grammatical properties

    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
    496
    +0.20
    0.8%
    447
    +0.17
    0.7%
    688
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    61
    +0.20
    0.09
    596
    +0.17
    0.08
    295
    +0.15
    0.07
    Negative Logits
    ï¸
    -0.92
     Lauder
    -0.89
    ģĸ
    -0.87
     Beir
    -0.81
     Haram
    -0.77
     Bulldogs
    -0.77
     Unic
    -0.77
    ¨
    -0.76
     Quarterly
    -0.75
     Baptist
    -0.75
    POSITIVE LOGITS
    icum
    1.53
    ifiable
    1.49
    ding
    1.47
    elled
    1.41
    ifiers
    1.39
    ifications
    1.38
    ded
    1.37
    ules
    1.36
    ifies
    1.34
    ulo
    1.29
    Activations Density 7.560%

    No Known Activations