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. 0-RES-JB
    6. 8666
    Prev
    Next
    INDEX
    Explanations

    references to the university or sports team "Auburn"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Auburn University football program and its associated elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brill
    -0.78
     crypt
    -0.76
     Crypt
    -0.75
     STOR
    -0.73
     roaming
    -0.71
    typ
    -0.70
     Tablet
    -0.68
     Phant
    -0.67
    riers
    -0.66
     Zombies
    -0.66
    POSITIVE LOGITS
     Auburn
    2.72
     Mend
    1.56
     Alfred
    1.16
     Fresno
    1.11
     Barber
    1.09
    plant
    1.08
    endra
    1.04
    endo
    0.97
     Pasadena
    0.97
     Bent
    0.97
    Activations Density 0.046%

    No Known Activations