© 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. 3441
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms related to geology, geography, and mineralogy

    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
    746
    +0.10
    0.5%
    7
    +0.09
    0.5%
    386
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.05
    288
    +0.09
    0.06
    659
    +0.09
    0.04
    Negative Logits
    ©¶æ
    -0.60
     Doctrine
    -0.57
    casters
    -0.56
    spect
    -0.55
    deals
    -0.54
    pty
    -0.54
    iculty
    -0.54
     Doct
    -0.54
    chron
    -0.53
    chuk
    -0.53
    POSITIVE LOGITS
    esis
    1.17
    furt
    1.05
    EMENT
    0.88
    arians
    0.73
    arian
    0.71
    etic
    0.69
    etics
    0.64
    udo
    0.60
    orship
    0.60
    ataka
    0.60
    Activations Density 0.440%

    No Known Activations