© 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. 11-RES-JB
    11. 2297
    Prev
    Next
    INDEX
    Explanations

    web links and handles on social media platforms

    oai_token-act-pair · gpt-3.5-turbo

    specific patterns of letters or sequences that resemble identifiers or codes

    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
    t
    -0.93
    dor
    -0.87
    d
    -0.86
    vich
    -0.85
    c
    -0.83
    matically
    -0.83
    tes
    -0.82
    tor
    -0.82
    tr
    -0.79
    ttes
    -0.78
    POSITIVE LOGITS
    velength
    1.03
    Ô
    0.99
    NULL
    0.87
    iley
    0.87
    usterity
    0.86
    uthor
    0.86
    ibo
    0.85
    emon
    0.85
    issance
    0.83
    Ta
    0.82
    Activations Density 0.144%

    No Known Activations