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. 12738
    Prev
    Next
    INDEX
    Explanations

    mentions of the Green Bay Packers

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific Pokémon names or identifiers

    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
    nces
    -0.86
    orically
    -0.74
    Downloadha
    -0.73
    ysis
    -0.73
    Reloaded
    -0.69
     aver
    -0.65
    ymes
    -0.63
    nce
    -0.63
    rator
    -0.63
    gerald
    -0.61
    POSITIVE LOGITS
    grass
    1.09
    leaf
    1.03
     Lantern
    1.00
    baum
    1.00
    wich
    1.00
    belt
    0.95
    boro
    0.91
    wald
    0.91
    houses
    0.89
    house
    0.88
    Activations Density 0.023%

    No Known Activations