© 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. 20941
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names, titles, and positions related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals, particularly with a focus on their titles and roles

    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
    externalActionCode
    -0.85
     broom
    -0.84
    orth
    -0.75
    grain
    -0.71
    soDeliveryDate
    -0.69
     lift
    -0.69
    ppo
    -0.69
    oup
    -0.68
     perf
    -0.68
    ĸļ
    -0.67
    POSITIVE LOGITS
    David
    2.03
     David
    2.01
     david
    1.83
     DAV
    1.58
     Dave
    1.41
    Dave
    1.34
     Davidson
    1.31
    avid
    1.22
     Cameron
    1.00
     Jonathan
    0.95
    Activations Density 0.174%

    No Known Activations