© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 4228
    Prev
    Next
    INDEX
    Explanations

    adjectives describing appropriateness or suitability

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fitting" used to describe appropriateness or suitability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ying
    -0.71
    cipline
    -0.69
    cipl
    -0.67
     carrot
    -0.66
    ulhu
    -0.59
    avez
    -0.58
    cler
    -0.57
    eger
    -0.57
    cheat
    -0.56
    stals
    -0.56
    POSITIVE LOGITS
     fitting
    1.03
    fit
    0.99
    fitting
    0.97
     snug
    0.84
     fit
    0.81
    Fit
    0.80
    fits
    0.80
    fitted
    0.77
    ably
    0.75
     fitted
    0.73
    Activations Density 0.009%

    No Known Activations