© 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. 2-RES-JB
    11. 4499
    Prev
    Next
    INDEX
    Explanations

    references to specific URLs and online profiles

    oai_token-act-pair · gpt-3.5-turbo

    references to high levels of activity or mentions related to specific individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nces
    -0.87
     proto
    -0.67
     Izan
    -0.66
     nomine
    -0.66
     Minority
    -0.64
     Phant
    -0.63
    e
    -0.62
     pole
    -0.62
     Debor
    -0.61
     Palestin
    -0.59
    POSITIVE LOGITS
    stein
    1.06
    mann
    0.97
    hl
    0.97
    uci
    0.93
    iere
    0.91
    igh
    0.89
    endor
    0.89
    iday
    0.89
    alm
    0.87
    uff
    0.86
    Activations Density 0.008%

    No Known Activations