© 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. 9-RES-JB
    11. 7405
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of people, specifically with words like "someone," "somebody," or "someone" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to undefined or vague individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tnc
    -0.93
    UV
    -0.71
    ean
    -0.70
    osterone
    -0.69
    iven
    -0.66
    Rom
    -0.66
    Vert
    -0.65
    urer
    -0.64
    effect
    -0.63
    imon
    -0.62
    POSITIVE LOGITS
     else
    1.42
    Else
    1.07
     stole
    1.01
    else
    0.98
     forgot
    0.94
     Else
    0.91
     intervened
    0.83
     coined
    0.83
     wants
    0.81
     wrote
    0.81
    Activations Density 0.104%

    No Known Activations