© 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. 1876
    Prev
    Next
    INDEX
    Explanations

    phrase "all the way"

    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
    727
    +0.16
    0.5%
    9
    +0.14
    0.5%
    706
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.16
    0.03
    9
    +0.14
    0.03
    50
    +0.14
    0.02
    Negative Logits
    ĪĴ
    -1.37
    ĸļ
    -1.29
    orem
    -1.19
    ister
    -1.13
     Flavoring
    -1.09
    erves
    -1.09
    uster
    -1.08
    igel
    -1.04
    uci
    -1.00
    erve
    -0.96
    POSITIVE LOGITS
    ward
    1.15
    points
    1.14
    forth
    1.14
    forward
    1.08
    point
    1.03
    finding
    0.99
    around
    0.98
    fare
    0.97
    assed
    0.94
    stones
    0.94
    Activations Density 0.160%

    No Known Activations