© 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. 8-RES-JB
    11. 3119
    Prev
    Next
    INDEX
    Explanations

    attributes related to regions or territories

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to geography and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ponds
    -0.78
     watering
    -0.66
     centrif
    -0.63
    utra
    -0.63
     pond
    -0.62
     marrow
    -0.61
     sharp
    -0.60
    ĸļ
    -0.59
     mouths
    -0.57
     streams
    -0.57
    POSITIVE LOGITS
    alion
    0.79
    cia
    0.77
    ilial
    0.76
    ç
    0.74
    naire
    0.72
    rique
    0.71
    ciation
    0.71
    ibus
    0.70
    itely
    0.69
    ctive
    0.68
    Activations Density 0.617%

    No Known Activations