Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 10266
    Prev
    Next
    INDEX
    Explanations

    mentions of the state of Indiana

    oai_token-act-pair · gpt-3.5-turbo

    references to Indiana and its historical and political context

    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
    Ruby
    -1.18
     Ruby
    -1.07
     Copenhagen
    -0.97
    Nar
    -0.97
    Weiss
    -0.97
     Haf
    -0.93
    Ber
    -0.89
     Canucks
    -0.87
     Cabrera
    -0.86
     Somalia
    -0.86
    POSITIVE LOGITS
     Indiana
    2.27
    Indiana
    2.22
     Indianapolis
    2.12
     Indy
    2.08
     Pence
    1.94
     IU
    1.91
     Pacers
    1.65
     Purdue
    1.59
     Blooming
    1.55
     Ho
    1.40
    Activations Density 0.259%

    No Known Activations