© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11098
    Prev
    Next
    INDEX
    Explanations

    instances where something is being done by individual entities in a group setting

    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
    214
    +0.04
    0.4%
    212
    +0.03
    0.4%
    241
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    214
    +0.04
    0.04
    686
    +0.03
    0.03
    718
    +0.03
    0.03
    Negative Logits
     Recent
    -0.29
     Horizons
    -0.26
     Virt
    -0.26
     Sources
    -0.26
     Current
    -0.25
     VIDEOS
    -0.25
     Conditions
    -0.25
    etheless
    -0.25
     ITS
    -0.25
     Gran
    -0.25
    POSITIVE LOGITS
    aily
    0.29
     forg
    0.29
    lled
    0.28
     bat
    0.28
    eled
    0.27
    wagen
    0.26
    zu
    0.26
    aid
    0.25
    els
    0.25
    ando
    0.24
    Activations Density 0.113%

    No Known Activations