© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 5668
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'Fat' with varying emphasis on the letters

    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
    288
    +0.28
    1.0%
    421
    +0.19
    0.6%
    167
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.28
    0.07
    421
    +0.19
    0.04
    326
    +0.17
    0.05
    Negative Logits
    SPONSORED
    -1.10
    sers
    -1.09
     Vaugh
    -1.02
     Ascend
    -1.00
    ä
    -0.98
     Aerospace
    -0.97
     CFR
    -0.95
     Doct
    -0.93
     PV
    -0.93
     Rowling
    -0.91
    POSITIVE LOGITS
    igue
    1.65
    rition
    1.25
    ishes
    1.20
     cheeks
    1.19
    balls
    1.17
    tailed
    1.16
    hered
    1.15
     belly
    1.14
    fat
    1.13
    bag
    1.12
    Activations Density 0.793%

    No Known Activations