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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-RES-JB
    6. 8879
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific location, "Champaign"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location or event related to "Champ," particularly in an electoral context

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

    No Comments

    Negative Logits
    */(
    -0.91
     conflic
    -0.75
    duino
    -0.73
    gypt
    -0.73
     landsl
    -0.72
     stocking
    -0.72
     omission
    -0.71
    ©¶æ
    -0.70
     recess
    -0.70
     obser
    -0.68
    POSITIVE LOGITS
    agne
    1.82
    aign
    1.76
     Champ
    1.17
    Champ
    0.96
    xon
    0.84
    ione
    0.84
    neys
    0.79
    plain
    0.78
    lord
    0.77
    zilla
    0.74
    Activations Density 0.014%

    No Known Activations