© 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. 10907
    Prev
    Next
    INDEX
    Explanations

    terms related to computer science and mathematical logic

    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
    57
    +0.18
    0.7%
    659
    +0.14
    0.5%
    99
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.18
    0.13
    659
    +0.14
    0.11
    288
    +0.14
    0.14
    Negative Logits
    pmwiki
    -0.94
    istically
    -0.94
    piece
    -0.90
    icago
    -0.89
    talk
    -0.88
    uitous
    -0.86
    things
    -0.86
    ricane
    -0.83
    ipop
    -0.83
    uncle
    -0.83
    POSITIVE LOGITS
    alogy
    1.41
    agles
    1.23
    issance
    1.22
    utical
    1.21
    uve
    1.16
    utics
    1.12
    volent
    1.08
     Hof
    0.97
    ption
    0.97
    aves
    0.97
    Activations Density 2.369%

    No Known Activations