© 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. 1-RES-JB
    11. 22877
    Prev
    Next
    INDEX
    Explanations

    special characters grouped with other text and parentheses

    oai_token-act-pair · gpt-3.5-turbo

    closing parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omorphic
    -0.79
    itory
    -0.78
     mathemat
    -0.78
     answ
    -0.78
     commer
    -0.75
     guiActiveUn
    -0.74
    ciating
    -0.74
    ©¶æ
    -0.72
    asury
    -0.72
    ĵĺ
    -0.72
    POSITIVE LOGITS
    )].
    0.74
    )))
    0.73
    */
    0.69
    Conclusion
    0.68
    âĢ¦)
    0.67
     Frames
    0.65
     Syndicate
    0.65
    ])
    0.65
    arthy
    0.65
     Committees
    0.64
    Activations Density 0.155%

    No Known Activations