© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 13576
    Prev
    Next
    INDEX
    Explanations

    descriptions related to specific scenes or imagery in different stories

    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
    288
    +0.20
    0.9%
    580
    +0.12
    0.5%
    291
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.20
    0.38
    225
    +0.12
    0.15
    724
    +0.11
    0.20
    Negative Logits
    uana
    -0.79
    aiman
    -0.71
    verbs
    -0.70
     disadvant
    -0.69
    PUT
    -0.68
    sol
    -0.67
    Interest
    -0.66
    Fax
    -0.65
    ammy
    -0.63
     Booster
    -0.63
    POSITIVE LOGITS
     mund
    0.94
     mortals
    0.91
    enance
    0.89
     notwithstanding
    0.71
     pleasures
    0.71
    iously
    0.70
     souls
    0.69
     awaiting
    0.69
     thereof
    0.69
    rils
    0.69
    Activations Density 13.353%

    No Known Activations