© 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. 10-RES-JB
    11. 3219
    Prev
    Next
    INDEX
    Explanations

    locations, events, and people related to politics and public demonstrations

    oai_token-act-pair · gpt-3.5-turbo

    references to locations and events related to political and social gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.78
     pse
    -0.77
     probabilities
    -0.73
     hybrids
    -0.71
    itives
    -0.71
    lishes
    -0.70
     syndrome
    -0.69
    etimes
    -0.68
     listeners
    -0.67
     users
    -0.67
    POSITIVE LOGITS
     Museum
    1.41
     Hotel
    1.27
     courthouse
    1.19
     Library
    1.16
     Coliseum
    1.16
     Memorial
    1.16
     Statue
    1.15
     Theatre
    1.14
     Theater
    1.13
     Pavilion
    1.11
    Activations Density 0.318%

    No Known Activations