© 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. 11950
    Prev
    Next
    INDEX
    Explanations

    companies or organizations mentioned in tech or business news articles

    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%
    167
    +0.14
    0.5%
    359
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.21
    0.11
    288
    +0.14
    0.12
    346
    +0.13
    0.10
    Negative Logits
    geries
    -0.94
    berra
    -0.90
    tml
    -0.90
     captcha
    -0.90
    olulu
    -0.83
    ochemical
    -0.83
    drawn
    -0.81
    odic
    -0.80
    semble
    -0.80
     fri
    -0.80
    POSITIVE LOGITS
    's
    1.15
     Corporation
    1.11
    geist
    1.08
    HQ
    1.03
     Technologies
    1.02
    Corp
    1.01
    Gate
    0.99
     itself
    0.98
     Stores
    0.97
     Restaur
    0.97
    Activations Density 1.173%

    No Known Activations