© 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. 10-RES-JB
    11. 9995
    Prev
    Next
    INDEX
    Explanations

    phrases or proper nouns related to specific persons or events, potentially including medical conditions or political figures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ran"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    earable
    -0.65
    unin
    -0.62
    ready
    -0.62
    cember
    -0.61
    ornia
    -0.61
    ensor
    -0.59
    ensed
    -0.57
    ãĤī
    -0.57
     moderation
    -0.56
    £ı
    -0.56
    POSITIVE LOGITS
    vier
    1.03
    igans
    0.92
    thal
    0.90
    ium
    0.90
    ially
    0.88
    ial
    0.87
    ching
    0.86
    tenance
    0.84
    ieties
    0.83
    iety
    0.83
    Activations Density 0.036%

    No Known Activations