© 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. 3-RES-JB
    11. 10362
    Prev
    Next
    INDEX
    Explanations

    descriptions of a situation or topic

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of a "picture" or portrayal of a situation or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endez
    -0.82
    amily
    -0.80
    iant
    -0.77
    ajor
    -0.74
    orne
    -0.72
    iencies
    -0.70
    aughs
    -0.68
    cffff
    -0.68
    ggles
    -0.67
    bard
    -0.67
    POSITIVE LOGITS
    picture
    1.09
     picture
    0.94
     Picture
    0.89
    >>>>>>>>
    0.82
     depicting
    0.81
    journal
    0.81
    Picture
    0.81
     mosaic
    0.73
     img
    0.73
     illustration
    0.73
    Activations Density 0.017%

    No Known Activations