© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 14109
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical surroundings or objects

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    196
    +0.13
    0.5%
    393
    +0.13
    0.5%
    499
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.13
    0.10
    608
    +0.13
    0.07
    196
    +0.13
    0.04
    Negative Logits
     Awakens
    -0.80
     Moons
    -0.80
    Scale
    -0.75
    Finish
    -0.75
     sailed
    -0.74
    yout
    -0.74
     dives
    -0.73
    arma
    -0.71
     ended
    -0.70
    ohan
    -0.70
    POSITIVE LOGITS
     priceless
    0.93
    aband
    0.89
     innumerable
    0.76
    metadata
    0.75
     ample
    0.75
     plethora
    0.75
     scant
    0.74
     palpable
    0.74
    LEY
    0.73
    chel
    0.73
    Activations Density 1.540%

    No Known Activations