© 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. 1786
    Prev
    Next
    INDEX
    Explanations

    web links

    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
    89
    +0.06
    0.5%
    610
    +0.05
    0.5%
    575
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    670
    +0.06
    0.01
    331
    +0.05
    0.01
    717
    +0.05
    0.01
    Negative Logits
    lag
    -0.38
    machine
    -0.34
     controversies
    -0.34
    Interstitial
    -0.33
    Sensor
    -0.33
    lov
    -0.33
    chall
    -0.33
    nir
    -0.32
     Topics
    -0.32
     ARTICLE
    -0.32
    POSITIVE LOGITS
     recogn
    0.39
    ¿½
    0.38
    ijah
    0.38
    ynt
    0.35
    ryce
    0.35
    ilyn
    0.34
    YING
    0.34
    reating
    0.34
    athering
    0.34
    aptop
    0.33
    Activations Density 0.006%

    No Known Activations