© 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. 2112
    Prev
    Next
    INDEX
    Explanations

    names of individuals named "Marcus"

    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
    659
    +0.17
    0.6%
    173
    +0.13
    0.4%
    134
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.13
    326
    +0.13
    0.10
    659
    +0.13
    0.10
    Negative Logits
    ships
    -1.28
    ITNESS
    -1.19
    sworth
    -1.13
    itness
    -1.05
    ociation
    -1.04
    ship
    -1.03
    */(
    -1.03
    boarding
    -1.01
    yip
    -1.01
    ega
    -1.00
    POSITIVE LOGITS
     Aure
    1.56
    armor
    1.16
    ques
    1.13
    Marcus
    1.10
    cles
    1.06
    cius
    1.03
    ias
    1.00
    interstitial
    0.97
    kson
    0.96
    HAEL
    0.96
    Activations Density 1.581%

    No Known Activations