© 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. 3614
    Prev
    Next
    INDEX
    Explanations

    technological terms, specific data, and company-related information

    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
    466
    +0.14
    0.6%
    404
    +0.13
    0.6%
    98
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    466
    +0.14
    0.06
    404
    +0.13
    0.06
    373
    +0.12
    -0.02
    Negative Logits
     loophole
    -0.68
     conveniently
    -0.63
     amygdala
    -0.60
     +/-
    -0.59
    swick
    -0.59
    perture
    -0.59
    EEK
    -0.58
    ernel
    -0.58
     skilled
    -0.58
    ratom
    -0.57
    POSITIVE LOGITS
    backer
    0.75
    Īè
    0.75
    ophone
    0.72
    etary
    0.70
    ublic
    0.69
    andom
    0.67
    heed
    0.67
    nant
    0.66
    lette
    0.66
    Wire
    0.65
    Activations Density 0.404%

    No Known Activations