© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 5798
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to information technology and electronics

    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
    87
    +0.27
    2.7%
    266
    +0.11
    1.1%
    288
    +0.06
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.27
    -0.19
    459
    +0.11
    0.35
    464
    +0.06
    0.27
    Negative Logits
    actionDate
    -0.34
    ãĥ©ãĥ³
    -0.29
    Rh
    -0.29
    Lev
    -0.28
    rss
    -0.27
    rehens
    -0.27
    lee
    -0.25
     Zhang
    -0.25
    ++++++++++++++++
    -0.25
    la
    -0.25
    POSITIVE LOGITS
    senal
    0.36
    schild
    0.32
    uterte
    0.29
    foundland
    0.29
    ahime
    0.28
     equivalents
    0.28
     destro
    0.27
     treasury
    0.27
     fundamentals
    0.27
     bandwagon
    0.26
    Activations Density 38.359%

    No Known Activations