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

    Neuronpedia

    Jacobian LensNEW
    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. 14771
    Prev
    Next
    INDEX
    Explanations

    phrases indicating information or guidance provided to someone

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "told" indicating reported information or communication

    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
    anu
    -0.61
    insula
    -0.61
     ILCS
    -0.60
    dayName
    -0.59
    aho
    -0.59
    hift
    -0.58
    ockets
    -0.58
    vous
    -0.56
    APTER
    -0.56
    plete
    -0.55
    POSITIVE LOGITS
     by
    1.33
    by
    0.94
     orally
    0.88
     BY
    0.85
     repeatedly
    0.82
     beforehand
    0.82
     By
    0.80
     aback
    0.79
    By
    0.78
     differently
    0.71
    Activations Density 0.044%

    No Known Activations