© 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 Local
    9. 6-RES_SCL-AJT
    11. 35926
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.13
    0.5%
    393
    +0.13
    0.5%
    75
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.13
    0.16
    640
    +0.13
    0.18
    566
    +0.13
    0.08
    Negative Logits
     Lau
    -0.86
    ©¶æ¥µ
    -0.82
    é¾
    -0.80
    ĨĴ
    -0.79
    ingu
    -0.76
    conserv
    -0.75
    Mount
    -0.75
    efer
    -0.74
    iculty
    -0.72
    iche
    -0.71
    POSITIVE LOGITS
     kindly
    1.23
     sir
    1.20
     guys
    1.11
     gentlemen
    0.98
     welcome
    0.96
     gracious
    0.93
    're
    0.89
    giving
    0.86
    RS
    0.83
    ा
    0.82
    Activations Density 7.991%

    No Known Activations