© 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. 4-RES-JB
    11. 2283
    Prev
    Next
    INDEX
    Explanations

    events or productions that are being featured or highlighted

    oai_token-act-pair · gpt-3.5-turbo

    events or activities that involve a notable feature or attraction

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

    No Comments

    Negative Logits
    sis
    -0.89
    sett
    -0.82
    hood
    -0.77
    ilit
    -0.76
     exting
    -0.75
     srf
    -0.72
    si
    -0.70
    berman
    -0.65
    abi
    -0.65
     tiss
    -0.65
    POSITIVE LOGITS
     prominently
    1.11
    Feature
    0.76
     features
    0.75
    Featured
    0.74
    Features
    0.71
    features
    0.71
    :-
    0.70
    âĸ¬âĸ¬
    0.69
     attractions
    0.68
     Features
    0.67
    Activations Density 0.039%

    No Known Activations