© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 576
    Prev
    Next
    INDEX
    Explanations

    unrelated and seemingly random patterns of characters, it doesn't seem to have a specific focus

    oai_token-act-pair · gpt-3.5-turbo

    indications of an action or event occurring

    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
     neighb
    -0.75
    nesday
    -0.69
     destro
    -0.67
    ©¶æ
    -0.66
    xual
    -0.62
    undai
    -0.62
    hement
    -0.60
     herself
    -0.60
     citiz
    -0.60
     thous
    -0.60
    POSITIVE LOGITS
    PRESS
    0.83
     largeDownload
    0.82
    Posted
    0.79
    Interested
    0.78
    Click
    0.78
    pmwiki
    0.76
    SELECT
    0.75
    Joined
    0.75
    Details
    0.74
    Disclaimer
    0.74
    Activations Density 0.213%

    No Known Activations