© 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. 2077
    Prev
    Next
    INDEX
    Explanations

    the word "que" in text

    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
    526
    +0.19
    0.7%
    649
    +0.18
    0.7%
    706
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.19
    0.07
    404
    +0.18
    0.05
    288
    +0.16
    0.07
    Negative Logits
    ERAL
    -0.96
    ãĥŁ
    -0.93
    ãĥ³ãĤ¸
    -0.91
    restrial
    -0.91
     Hers
    -0.89
     Hebrew
    -0.89
     STATS
    -0.89
    olesterol
    -0.85
    ructose
    -0.84
    wig
    -0.84
    POSITIVE LOGITS
    erness
    1.41
     Que
    1.23
    uing
    1.18
    zon
    1.13
    ued
    1.11
    Que
    1.06
    ues
    1.05
    edo
    1.02
    iu
    1.01
    que
    1.00
    Activations Density 1.150%

    No Known Activations