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. 16861
    Prev
    Next
    INDEX
    Explanations

    political figures' names and numbers

    oai_token-act-pair · gpt-3.5-turbo

    specific individuals and their associated numerical statistics or percentages

    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
     Seah
    -0.68
     Mole
    -0.63
     Realms
    -0.61
     Assassins
    -0.61
     successors
    -0.61
     Bucket
    -0.61
     Gates
    -0.60
     Omega
    -0.60
     Millennium
    -0.60
     Timeline
    -0.60
    POSITIVE LOGITS
    advertising
    0.90
     37
    0.90
    almost
    0.84
     33
    0.84
     47
    0.82
     53
    0.82
     63
    0.81
     38
    0.81
     27
    0.80
     39
    0.80
    Activations Density 0.170%

    No Known Activations