© 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. 1797
    Prev
    Next
    INDEX
    Explanations

    keywords related to media and technology issues

    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
    288
    +0.21
    0.7%
    132
    +0.19
    0.6%
    336
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.21
    0.06
    132
    +0.19
    0.04
    662
    +0.15
    0.05
    Negative Logits
    ranch
    -1.09
    anks
    -1.00
    cker
    -0.94
     Rasmussen
    -0.94
    nob
    -0.91
    lier
    -0.91
     Salvador
    -0.90
    abouts
    -0.90
    é¾įå
    -0.90
    cair
    -0.88
    POSITIVE LOGITS
    eval
    1.48
     VIDEOS
    1.15
     playback
    1.14
    wiki
    1.09
    natureconservancy
    1.01
    fax
    1.01
     outlets
    1.00
    medi
    1.00
     caption
    0.97
     Matters
    0.97
    Activations Density 0.513%

    No Known Activations