© 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. 11338
    Prev
    Next
    INDEX
    Explanations

    names of people and locations associated with a news story

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals in a narrative context

    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
     herself
    -1.33
     her
    -1.14
    She
    -1.12
     she
    -1.08
    kaya
    -1.06
     SHE
    -1.03
     hers
    -1.01
     She
    -1.01
    ova
    -1.00
    Her
    -0.98
    POSITIVE LOGITS
    His
    1.12
     his
    1.11
    his
    1.04
     His
    1.02
     he
    1.00
     himself
    0.99
    He
    0.96
     He
    0.93
     Jr
    0.87
    Jr
    0.85
    Activations Density 0.896%

    No Known Activations