© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12772
    Prev
    Next
    INDEX
    Explanations

    actions or sequences of events done by individuals

    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
    +0.32
    1.6%
    393
    +0.10
    0.5%
    706
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.32
    0.07
    393
    +0.10
    0.20
    566
    +0.09
    0.08
    Negative Logits
     impossibility
    -0.61
     belief
    -0.57
     Bout
    -0.55
    tery
    -0.55
     Venezuel
    -0.54
     believers
    -0.54
     Presence
    -0.54
    assed
    -0.54
     Benson
    -0.53
     competence
    -0.53
    POSITIVE LOGITS
     proceeded
    1.12
     proceeds
    0.87
     proceed
    0.82
     promptly
    0.79
    ŃĶ
    0.75
    ļéĨĴ
    0.75
     transitioned
    0.73
    veland
    0.73
     conclud
    0.72
    Ń·
    0.70
    Activations Density 9.440%

    No Known Activations