© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3594
    Prev
    Next
    INDEX
    Explanations

    mentions of politicians by their titles with a period followed by a high activation value

    oai_token-act-pair · gpt-3.5-turbo

    references to senators and political figures

    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
    hess
    -0.73
    rawdownloadcloneembedreportprint
    -0.70
    0200
    -0.69
     0004
    -0.67
    1007
    -0.65
     showc
    -0.65
    bender
    -0.63
     behavi
    -0.63
     unequ
    -0.60
    nesses
    -0.60
    POSITIVE LOGITS
     Dianne
    1.30
     Lindsey
    1.28
     Bernie
    1.26
     Patty
    1.24
     Rand
    1.20
     Kirst
    1.19
     Ted
    1.18
     Marco
    1.15
     Lamar
    1.15
     Jeanne
    1.15
    Activations Density 0.030%

    No Known Activations