© 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. 14430
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms

    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
    41
    +0.08
    0.4%
    446
    +0.08
    0.4%
    79
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.08
    0.04
    545
    +0.08
    0.03
    232
    +0.08
    0.03
    Negative Logits
    phrine
    -0.91
     bubbles
    -0.68
    apy
    -0.65
    bub
    -0.65
     bubble
    -0.64
     pods
    -0.60
    nery
    -0.58
     Bubble
    -0.58
     balloons
    -0.57
     bottled
    -0.56
    POSITIVE LOGITS
    ruction
    0.66
    ª
    0.64
    uration
    0.63
    ļé
    0.62
    inct
    0.60
    istrate
    0.59
    lie
    0.59
    itness
    0.58
    allah
    0.58
    ļ
    0.57
    Activations Density 0.236%

    No Known Activations