© 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. 40064
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and instructions

    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
    +0.24
    1.4%
    253
    +0.08
    0.5%
    157
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    293
    +0.24
    0.19
    157
    +0.08
    0.21
    675
    +0.08
    0.19
    Negative Logits
     disadvant
    -0.70
     vulner
    -0.70
     accomp
    -0.62
     advis
    -0.62
     mathemat
    -0.61
     princ
    -0.61
     traged
    -0.59
     incent
    -0.58
     fundament
    -0.57
     incorpor
    -0.56
    POSITIVE LOGITS
    ï¸ı
    0.76
    ï¸
    0.73
    RW
    0.66
    \":
    0.63
    ½
    0.59
    é¾į
    0.59
    cffffcc
    0.58
    ished
    0.58
    âĶĢâĶĢ
    0.58
    ÙĦ
    0.57
    Activations Density 9.553%

    No Known Activations