© 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. 3021
    Prev
    Next
    INDEX
    Explanations

    instances of one entity providing something to another

    oai_token-act-pair · gpt-3.5-turbo

    actions related to giving or providing something

    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
    psc
    -0.75
    inav
    -0.62
    urities
    -0.61
     imagin
    -0.61
     collisions
    -0.59
     WATCHED
    -0.58
    ski
    -0.58
    .","
    -0.57
     compr
    -0.57
    LINE
    -0.57
    POSITIVE LOGITS
     assurances
    0.89
     us
    0.87
     him
    0.86
     them
    0.78
    AMA
    0.73
     refunds
    0.70
     condolences
    0.70
     directions
    0.69
     me
    0.66
    HK
    0.66
    Activations Density 0.200%

    No Known Activations