© 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. 2119
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to various levels of a scale or range

    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
    393
    +0.28
    1.1%
    170
    +0.17
    0.7%
    561
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    170
    +0.28
    0.10
    669
    +0.17
    0.08
    362
    +0.13
    0.09
    Negative Logits
    paces
    -1.03
    nis
    -0.91
    nets
    -0.91
    ername
    -0.91
    books
    -0.90
    ãĤ¼ãĤ¦ãĤ¹
    -0.90
     Cosponsors
    -0.88
    uristic
    -0.85
    ettes
    -0.85
    adelphia
    -0.84
    POSITIVE LOGITS
     interest
    1.10
     accomplishment
    1.02
     exposure
    1.02
     protection
    1.01
     tension
    1.01
     maturity
    1.01
     activity
    0.98
     success
    0.96
     parity
    0.96
     professionalism
    0.95
    Activations Density 1.266%

    No Known Activations