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. 9-RES-JB
    6. 4068
    Prev
    Next
    INDEX
    Explanations

    the word "ot" or "ot" followed by a single-digit number

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "ot" as part of various technical or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SOURCE
    -0.69
     proportions
    -0.69
     versa
    -0.57
     Boat
    -0.56
     motives
    -0.55
     galvan
    -0.55
    vier
    -0.53
     misunder
    -0.53
    interstitial
    -0.53
     seeker
    -0.53
    POSITIVE LOGITS
    tery
    1.10
    assium
    1.10
    ting
    1.07
    rans
    1.03
    opia
    1.00
    ainment
    1.00
    oxicity
    0.97
    zeb
    0.95
     Unch
    0.95
    eca
    0.94
    Activations Density 0.065%

    No Known Activations