© 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. 10-RES-JB
    11. 6676
    Prev
    Next
    INDEX
    Explanations

    mention of city councils and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to city council members and councils

    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
     Typh
    -0.78
     Jihad
    -0.69
     Abu
    -0.68
    riott
    -0.67
     smugglers
    -0.67
     Pax
    -0.66
     Himal
    -0.65
    zsche
    -0.65
     caliphate
    -0.63
     nerv
    -0.63
    POSITIVE LOGITS
    member
    1.28
    woman
    1.23
     unanimously
    1.19
     chambers
    1.07
     adjourn
    1.07
    members
    1.05
     subcommittee
    0.97
     Appropriations
    0.93
     approves
    0.92
     Member
    0.90
    Activations Density 0.100%

    No Known Activations