© 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. 40410
    Prev
    Next
    INDEX
    Explanations

    instances of ratios or percentages

    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
    +0.13
    0.6%
    616
    +0.11
    0.5%
    393
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    22
    +0.13
    0.18
    640
    +0.11
    0.27
    123
    +0.11
    0.14
    Negative Logits
    76561
    -0.62
     christ
    -0.59
     heights
    -0.58
    WHERE
    -0.57
     vag
    -0.56
     freed
    -0.56
    0000000000000000
    -0.55
     distances
    -0.55
     sounding
    -0.53
     architectures
    -0.53
    POSITIVE LOGITS
    organic
    1.08
    patient
    1.05
    clusions
    1.00
    ordinate
    0.99
    clusively
    0.97
    animate
    0.96
    escap
    0.94
    efficiency
    0.93
    humane
    0.88
    clud
    0.88
    Activations Density 11.587%

    No Known Activations