© 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. 2-RES-JB
    11. 9495
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures in positions of authority, particularly mayors

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "mayor."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opter
    -0.93
    bra
    -0.84
    endish
    -0.82
    ibaba
    -0.79
    phal
    -0.78
    condition
    -0.78
    reen
    -0.77
    ener
    -0.76
    arial
    -0.75
    uld
    -0.75
    POSITIVE LOGITS
     mayor
    1.13
     Mayor
    1.05
     councillor
    0.99
    alty
    0.94
    Mayor
    0.92
     mayoral
    0.91
     mayors
    0.84
     council
    0.78
     commissioner
    0.76
     franc
    0.70
    Activations Density 0.011%

    No Known Activations