© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 14320
    Prev
    Next
    INDEX
    Explanations

    terms related to physical appearance and characteristics, specifically focusing on facial features such as eyes, eyebrows, and the skull

    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
    497
    +0.19
    0.6%
    326
    +0.17
    0.6%
    99
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.19
    0.13
    288
    +0.17
    0.16
    592
    +0.15
    0.07
    Negative Logits
    FORM
    -1.12
    utics
    -1.11
    ×ķ
    -1.06
    fficiency
    -1.02
    utic
    -1.01
    unity
    -1.00
    Ò
    -1.00
    hesis
    -0.94
    È
    -0.94
    elsen
    -0.93
    POSITIVE LOGITS
    bones
    1.67
    bone
    1.35
     brow
    1.32
    tops
    1.20
    brow
    1.16
    mares
    1.13
    ed
    1.13
    line
    1.12
    flake
    1.10
    breaker
    1.08
    Activations Density 2.385%

    No Known Activations