© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 18530
    Prev
    Next
    INDEX
    Explanations

    questions about the origin or source of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that inquire about origins or sources

    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
    sav
    -0.75
    asio
    -0.64
    eatures
    -0.64
    iew
    -0.64
    ilt
    -0.64
    ilts
    -0.61
     Davidson
    -0.60
    bda
    -0.60
    cape
    -0.58
    roe
    -0.57
    POSITIVE LOGITS
     unst
    0.71
     from
    0.70
     FROM
    0.66
    From
    0.64
    owship
    0.64
     closest
    0.62
     From
    0.61
    ãĤ¼
    0.60
    oct
    0.60
    from
    0.59
    Activations Density 0.024%

    No Known Activations