© 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. 22611
    Prev
    Next
    INDEX
    Explanations

    mentions of specific events or actions attributed to individuals

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "at the."

    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
    hift
    -0.71
    forces
    -0.68
     depends
    -0.68
    Quantity
    -0.67
    ister
    -0.66
    tons
    -0.65
    utenant
    -0.63
     resided
    -0.63
    avorite
    -0.63
     suffered
    -0.61
    POSITIVE LOGITS
     outset
    1.33
     behest
    1.17
     helm
    1.04
     conclusion
    1.01
     ceremony
    1.00
     unveiling
    1.00
     podium
    0.98
     inauguration
    0.92
     height
    0.90
     forefront
    0.90
    Activations Density 0.114%

    No Known Activations