© 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. 13507
    Prev
    Next
    INDEX
    Explanations

    statistics related to sports performances

    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
    393
    +0.26
    0.9%
    640
    +0.20
    0.7%
    526
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    761
    +0.26
    0.07
    60
    +0.20
    0.07
    238
    +0.18
    0.07
    Negative Logits
    hops
    -0.91
    mite
    -0.88
    oult
    -0.87
    ieri
    -0.87
    mart
    -0.85
    atically
    -0.84
    lish
    -0.82
     excerpt
    -0.82
    orah
    -0.80
    hari
    -0.78
    POSITIVE LOGITS
     regard
    1.60
     regards
    1.59
    stood
    1.56
    drawn
    1.41
    draw
    1.35
    standing
    1.30
    holding
    1.28
     respect
    1.17
     impunity
    1.03
    åĤ
    1.01
    Activations Density 0.614%

    No Known Activations