© 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. 10-RES-JB
    11. 18813
    Prev
    Next
    INDEX
    Explanations

    specific instances where people or organizations are mentioned, possibly related to political or governmental contexts

    oai_token-act-pair · gpt-3.5-turbo

    repetitive occurrences of the definite article "the."

    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
    zona
    -1.13
    colored
    -1.03
     toward
    -0.95
    atl
    -0.93
     fueled
    -0.92
     gotten
    -0.91
     favorably
    -0.88
     centered
    -0.86
     recognizes
    -0.86
    LEASE
    -0.85
    POSITIVE LOGITS
     Tories
    1.54
     £
    1.53
     NHS
    1.53
     UK
    1.47
     organisation
    1.44
     Scottish
    1.42
     BBC
    1.39
     programme
    1.39
    resa
    1.38
     organisers
    1.37
    Activations Density 0.499%

    No Known Activations