© 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. 12967
    Prev
    Next
    INDEX
    Explanations

    references to the city of Milwaukee

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city of Milwaukee

    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
    choes
    -0.82
    ours
    -0.81
    arial
    -0.77
    rices
    -0.76
    rees
    -0.72
    ramid
    -0.72
    ugu
    -0.72
    alia
    -0.72
    antly
    -0.72
    oward
    -0.71
    POSITIVE LOGITS
     Bucks
    1.26
    waukee
    1.15
     Brewers
    1.05
     Milwaukee
    0.99
     County
    0.94
    sburgh
    0.92
     Rapids
    0.84
     Admir
    0.80
     Tornado
    0.79
    ipeg
    0.79
    Activations Density 0.006%

    No Known Activations