© 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. 22578
    Prev
    Next
    INDEX
    Explanations

    references to official meetings and events involving political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to political events and meetings

    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
    xual
    -0.88
    SO
    -0.77
    geist
    -0.76
    escription
    -0.74
    INAL
    -0.72
     gore
    -0.72
     certs
    -0.67
    piracy
    -0.67
    alties
    -0.66
    hemy
    -0.66
    POSITIVE LOGITS
     Oval
    1.24
     Capitol
    1.24
     Pentagon
    1.18
     Dull
    1.16
     Eisenhower
    1.09
     White
    1.06
     Situation
    1.04
     CIA
    1.02
     Washington
    1.00
     Roosevelt
    1.00
    Activations Density 0.248%

    No Known Activations