© 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. 7943
    Prev
    Next
    INDEX
    Explanations

    negations by identifying instances of the word "not" and "never"

    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
    +0.17
    0.7%
    383
    +0.15
    0.6%
    616
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.17
    0.07
    544
    +0.15
    0.07
    200
    +0.12
    0.08
    Negative Logits
    éĥ
    -0.98
    å¥
    -0.91
    ä¿
    -0.88
    åº
    -0.88
    Origin
    -0.87
    Sword
    -0.87
     Presence
    -0.86
    çļ
    -0.86
    wives
    -0.85
    oided
    -0.84
    POSITIVE LOGITS
     necessarily
    1.38
    icable
    1.27
     exactly
    1.17
    hin
    1.15
    epad
    1.14
     quite
    1.08
     really
    1.08
    icably
    1.05
    orious
    1.04
     easy
    1.02
    Activations Density 0.696%

    No Known Activations