© 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. 9313
    Prev
    Next
    INDEX
    Explanations

    references to shooting or throwing accurately

    oai_token-act-pair · gpt-3.5-turbo

    references to three-point shots in basketball

    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
    creen
    -0.86
     unequ
    -0.78
     notor
    -0.77
    apore
    -0.70
    maid
    -0.68
    ARDS
    -0.67
    natureconservancy
    -0.65
    ocket
    -0.65
     Carbuncle
    -0.65
    phalt
    -0.65
    POSITIVE LOGITS
    edly
    0.98
    point
    0.88
    lessly
    0.85
    iasis
    0.80
    holder
    0.73
     conversion
    0.73
    pointers
    0.72
    ed
    0.70
    ion
    0.69
    llor
    0.69
    Activations Density 0.014%

    No Known Activations