© 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. 9-RES-JB
    11. 16032
    Prev
    Next
    INDEX
    Explanations

    terms related to personal traits or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical and behavioral traits or characteristics

    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
    endar
    -0.82
    endars
    -0.76
    source
    -0.76
    foreseen
    -0.71
    hand
    -0.71
    erva
    -0.69
    bilt
    -0.69
    glers
    -0.65
     Deals
    -0.64
    displayText
    -0.64
    POSITIVE LOGITS
     traits
    1.25
     characteristics
    1.09
     qualities
    1.00
     trait
    0.99
     characteristic
    0.98
     predis
    0.86
     attributes
    0.86
    istics
    0.85
     distinguishing
    0.85
     weaknesses
    0.80
    Activations Density 0.090%

    No Known Activations