© 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 EvalsExportsinterp-engineNEWAPI 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. 14419
    Prev
    Next
    INDEX
    Explanations

    personal traits or actions related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual and their actions or statements

    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
     Depth
    -0.69
    onica
    -0.69
    Luck
    -0.68
    processing
    -0.67
    UME
    -0.66
    static
    -0.66
    sufficient
    -0.66
     Presence
    -0.65
    growth
    -0.64
    --+
    -0.64
    POSITIVE LOGITS
     advocated
    1.44
     campaigned
    1.40
     preached
    1.34
     vowed
    1.28
     denounced
    1.24
     championed
    1.23
     founded
    1.22
     pledged
    1.20
     urged
    1.18
     toured
    1.17
    Activations Density 0.417%

    No Known Activations