© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-JB
    11. 14502
    Prev
    Next
    INDEX
    Explanations

    words related to amazement or astonishment

    oai_token-act-pair · gpt-3.5-turbo

    words related to being impressed or astonished

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    女
    -0.68
     mend
    -0.60
    itimate
    -0.60
     equ
    -0.58
    abor
    -0.56
    ocratic
    -0.55
     hone
    -0.55
     crops
    -0.55
     Boh
    -0.54
    onduct
    -0.54
    POSITIVE LOGITS
    azed
    1.10
    aze
    1.07
    aughs
    0.85
    ecake
    0.84
    geoning
    0.82
    azing
    0.81
    ï¸
    0.80
     Decay
    0.80
    urous
    0.78
    eker
    0.77
    Activations Density 0.007%

    No Known Activations