© 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. 12404
    Prev
    Next
    INDEX
    Explanations

    traits or characteristics associated with different attributes or qualities in individuals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to traits and characteristics

    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
    lins
    -0.68
    endars
    -0.68
    endar
    -0.68
    source
    -0.66
     convol
    -0.63
    bilt
    -0.63
     enthusi
    -0.61
    arger
    -0.61
    ollo
    -0.60
    psc
    -0.60
    POSITIVE LOGITS
     traits
    1.18
     characteristic
    1.08
     trait
    1.07
    hered
    1.00
     exhibited
    0.94
     predis
    0.94
     distinguishing
    0.92
     characteristics
    0.91
     conferred
    0.91
     inherited
    0.88
    Activations Density 0.138%

    No Known Activations