© 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. 3576
    Prev
    Next
    INDEX
    Explanations

    words related to cause and effect, particularly focusing on the results or outcomes of specific actions or events

    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
    679
    +0.23
    0.8%
    288
    +0.15
    0.5%
    665
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    542
    +0.23
    0.04
    324
    +0.15
    0.03
    679
    +0.14
    0.04
    Negative Logits
     Straw
    -1.00
    pent
    -0.99
    enta
    -0.90
     lineback
    -0.89
     Falk
    -0.88
     Bees
    -0.85
    abases
    -0.85
    vae
    -0.83
    sites
    -0.82
    vette
    -0.82
    POSITIVE LOGITS
    uary
    1.04
    :{
    1.01
    ainer
    1.00
    iments
    1.00
    gha
    1.00
    iment
    0.99
     thereof
    0.97
    ãĥł
    0.92
    ulator
    0.87
    ivity
    0.86
    Activations Density 0.546%

    No Known Activations