© 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. 11917
    Prev
    Next
    INDEX
    Explanations

    discussions about particular deals and agreements

    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
    +0.29
    1.1%
    679
    +0.13
    0.5%
    208
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    598
    +0.29
    0.09
    203
    +0.13
    0.10
    417
    +0.12
    0.09
    Negative Logits
    âĹ¼
    -0.86
    Tube
    -0.86
    mast
    -0.84
    eb
    -0.81
    ãĤµ
    -0.80
    vers
    -0.79
    Synopsis
    -0.78
    ice
    -0.76
    ving
    -0.72
    untarily
    -0.72
    POSITIVE LOGITS
     nevertheless
    1.59
     nonetheless
    1.37
     suffice
    1.27
     alas
    1.27
    tons
    1.27
     fortunately
    1.17
     luckily
    1.16
     thankfully
    1.14
     rather
    1.04
    tered
    1.03
    Activations Density 1.401%

    No Known Activations