© 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. 11-RES-JB
    11. 22648
    Prev
    Next
    INDEX
    Explanations

    words related to opposition, company operations, and decision-making processes

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with organizational structure and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Majesty
    -0.70
    '.
    -0.65
    %.
    -0.65
    =-=-=-=-=-=-=-=-
    -0.64
    onga
    -0.64
    enery
    -0.62
     PLEASE
    -0.61
    ?".
    -0.60
    `.
    -0.60
     Whilst
    -0.60
    POSITIVE LOGITS
     earlier
    0.90
     decades
    0.85
     reminiscent
    0.85
     last
    0.83
     modeled
    0.80
     during
    0.77
     shortly
    0.77
    fitted
    0.76
     championed
    0.75
    DragonMagazine
    0.75
    Activations Density 0.469%

    No Known Activations