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. 5637
    Prev
    Next
    INDEX
    Explanations

    mentions of "Texas A&M"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Texas A&M"

    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
     tipped
    -0.73
    ãĤ¡
    -0.72
     Eleven
    -0.65
     tips
    -0.64
     begg
    -0.63
     Guinness
    -0.62
    ãĥ´ãĤ¡
    -0.60
     Nep
    -0.58
     caps
    -0.57
     bruised
    -0.56
    POSITIVE LOGITS
    useum
    1.12
    asonic
    1.08
    ountain
    1.07
    insk
    1.05
    ormon
    1.05
    aiden
    1.02
    ISSION
    1.01
    ortal
    1.01
    ONEY
    1.00
    umbai
    0.98
    Activations Density 0.039%

    No Known Activations