© 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. 3409
    Prev
    Next
    INDEX
    Explanations

    words related to the chemical element Ruthenium

    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
    260
    +0.15
    0.5%
    526
    +0.15
    0.5%
    195
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.15
    0.08
    326
    +0.15
    0.08
    659
    +0.12
    0.07
    Negative Logits
    ĨĴ
    -1.27
    insula
    -1.08
    creen
    -1.08
    士
    -1.04
    é¾įå¥ij士
    -0.94
    £ı
    -0.94
    manship
    -0.93
    姫
    -0.92
    ãģ¦
    -0.91
    hops
    -0.91
    POSITIVE LOGITS
    acha
    1.28
    wered
    1.21
    zon
    1.21
    isin
    1.19
    ussian
    1.11
    Äį
    1.07
    caster
    1.07
    isma
    1.07
    ison
    1.06
    asion
    1.06
    Activations Density 1.093%

    No Known Activations