© 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. 2683
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to historical figures, locations, and events

    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
    383
    +0.16
    0.6%
    4
    +0.15
    0.5%
    649
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.16
    0.05
    48
    +0.15
    0.05
    288
    +0.15
    0.08
    Negative Logits
    é¾įå
    -0.95
    ICT
    -0.89
    Äĩ
    -0.84
    VW
    -0.80
    Aust
    -0.78
    BILITIES
    -0.78
    ACTED
    -0.78
     STOR
    -0.77
    BIL
    -0.77
    ictional
    -0.76
    POSITIVE LOGITS
    apeake
    1.61
    tons
    1.30
    ter
    1.17
    esville
    1.15
    tml
    1.12
    uled
    1.12
    rina
    1.10
    ding
    1.09
    een
    1.08
    nut
    1.06
    Activations Density 1.205%

    No Known Activations