© 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. 33105
    Prev
    Next
    INDEX
    Explanations

    phrases related to supernatural or science fiction content

    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
    +0.19
    0.8%
    151
    +0.11
    0.5%
    409
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.31
    575
    +0.11
    0.21
    540
    +0.10
    0.23
    Negative Logits
    helm
    -0.79
    anton
    -0.78
    lear
    -0.72
    lund
    -0.71
    cussion
    -0.70
     Bung
    -0.69
     herself
    -0.69
     Goff
    -0.69
    inson
    -0.69
     Mack
    -0.69
    POSITIVE LOGITS
     counterparts
    0.98
     counterpart
    0.94
     holdings
    0.90
     footprint
    0.88
     namesake
    0.84
     brethren
    0.83
     acronym
    0.78
     woes
    0.77
     predecessor
    0.77
     predecessors
    0.77
    Activations Density 14.766%

    No Known Activations