© 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. 39895
    Prev
    Next
    INDEX
    Explanations

    positive feedback and praise

    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
    420
    +0.10
    0.5%
    310
    +0.10
    0.5%
    128
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    730
    +0.10
    0.09
    130
    +0.10
    0.04
    167
    +0.09
    -0.02
    Negative Logits
    Downloadha
    -0.78
    olkien
    -0.73
    isSpecialOrderable
    -0.69
    代
    -0.65
    åĤ
    -0.63
    conservancy
    -0.61
     Juda
    -0.59
    udeau
    -0.57
    PsyNetMessage
    -0.57
    verend
    -0.57
    POSITIVE LOGITS
    er
    1.31
    ly
    1.29
    est
    1.10
    nesses
    0.95
    itudinal
    0.88
    ity
    0.87
    erate
    0.85
    ness
    0.83
    bye
    0.80
    erd
    0.77
    Activations Density 5.811%

    No Known Activations