© 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. 1-RES-JB
    11. 3102
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Poisson" or variants of it

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Poisson" and related terms in a statistical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kash
    -0.64
    EEK
    -0.64
     sorely
    -0.63
     behalf
    -0.61
     fair
    -0.61
    BY
    -0.60
     Judaism
    -0.60
     dime
    -0.60
     Yog
    -0.59
     cryptoc
    -0.58
    POSITIVE LOGITS
    isson
    1.62
    nette
    1.13
    naire
    0.99
    ance
    0.95
    inet
    0.88
    igans
    0.88
    clair
    0.87
    uous
    0.87
    iform
    0.86
    ette
    0.84
    Activations Density 0.006%

    No Known Activations