© 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. 4-RES-JB
    11. 492
    Prev
    Next
    INDEX
    Explanations

    titles or headings of articles or sections

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "Read more" or similar prompts for further information

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

    No Comments

    Negative Logits
    izons
    -0.78
    aza
    -0.69
    rette
    -0.69
     acquaintance
    -0.68
    gered
    -0.66
    unda
    -0.66
    boa
    -0.65
     subdivision
    -0.64
    zik
    -0.64
    arians
    -0.63
    POSITIVE LOGITS
     VIDEOS
    0.82
     WATCHED
    0.80
    atican
    0.74
    Featured
    0.72
     Recent
    0.71
    Images
    0.71
     What
    0.70
     Why
    0.69
     TBD
    0.68
     Photos
    0.68
    Activations Density 0.070%

    No Known Activations