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. 2-RES-JB
    6. 10981
    Prev
    Next
    INDEX
    Explanations

    mentions of specific universities and last names starting with "Cre" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Creighton" and its variations

    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
    DragonMagazine
    -0.86
    ãģ®éŃĶ
    -0.80
    insula
    -0.75
    manship
    -0.70
    iary
    -0.68
     Judd
    -0.67
     THR
    -0.67
    externalActionCode
    -0.66
     Heist
    -0.65
    ãĥ¼ãĥĨ
    -0.63
    POSITIVE LOGITS
     Cre
    1.19
    ighton
    1.12
    eny
    0.95
    Cre
    0.94
    cker
    0.87
    utz
    0.84
    aky
    0.83
    arest
    0.83
    mination
    0.82
    ande
    0.82
    Activations Density 0.006%

    No Known Activations