© 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 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. 12773
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific research and engineering

    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
    683
    +0.18
    0.6%
    59
    +0.15
    0.5%
    706
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    683
    +0.18
    0.07
    26
    +0.15
    0.06
    706
    +0.14
    0.05
    Negative Logits
    ĸļ
    -1.25
    sembly
    -1.02
    eenth
    -1.00
    chwitz
    -0.97
    ournal
    -0.97
    s
    -0.96
    sylvania
    -0.92
    VIDIA
    -0.91
    eneg
    -0.88
    acebook
    -0.87
    POSITIVE LOGITS
    jee
    1.28
    ds
    1.20
    rors
    1.18
    oute
    1.16
    nery
    1.14
    aton
    1.13
    ger
    1.13
    idge
    1.10
    rett
    1.10
    lein
    1.10
    Activations Density 0.852%

    No Known Activations