© 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. 15315
    Prev
    Next
    INDEX
    Explanations

    references to folk culture or folk-related concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to folk music or folk culture

    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
    xus
    -0.73
    Effective
    -0.71
    lain
    -0.64
    isites
    -0.62
     Reloaded
    -0.61
    inventoryQuantity
    -0.60
    xual
    -0.58
    rawdownloadcloneembedreportprint
    -0.58
    ONS
    -0.57
     RED
    -0.57
    POSITIVE LOGITS
    lore
    1.37
    folk
    1.24
    tale
    1.16
    lor
    1.14
    estone
    0.89
    worker
    0.88
    endor
    0.85
     folk
    0.85
     tales
    0.83
    ways
    0.82
    Activations Density 0.011%

    No Known Activations