© 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. 4133
    Prev
    Next
    INDEX
    Explanations

    information related to statistics and numerical data

    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
    507
    +0.11
    0.6%
    447
    +0.09
    0.5%
    627
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.11
    0.09
    314
    +0.09
    -0.07
    507
    +0.09
    0.16
    Negative Logits
     jaw
    -0.52
     corpus
    -0.52
     slate
    -0.52
    ĵĺ
    -0.50
     administr
    -0.50
     stir
    -0.49
     firsthand
    -0.49
     mult
    -0.49
    verse
    -0.48
     tension
    -0.48
    POSITIVE LOGITS
    uga
    0.62
     istg
    0.59
    ahon
    0.55
    livious
    0.55
    ccoli
    0.54
    amiya
    0.53
    oba
    0.53
    escription
    0.53
    izon
    0.53
    acteria
    0.52
    Activations Density 14.910%

    No Known Activations