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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15331
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Kobe", which could refer to the basketball player Kobe Bryant

    oai_token-act-pair · gpt-3.5-turbo

    references to Kobe Bryant

    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
    imental
    -0.78
    apore
    -0.75
    iments
    -0.73
    ancial
    -0.71
    entially
    -0.69
    imately
    -0.69
     shenan
    -0.69
    alez
    -0.67
    idy
    -0.64
     impossibility
    -0.64
    POSITIVE LOGITS
    obe
    0.98
    zeb
    0.94
    leck
    0.88
     Bryant
    0.87
    pedia
    0.81
    jamin
    0.81
    cean
    0.80
    isance
    0.74
     Breat
    0.72
    zes
    0.71
    Activations Density 0.013%

    No Known Activations