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. 8-RES-JB
    6. 16027
    Prev
    Next
    INDEX
    Explanations

    words related to the term "ball", such as names, locations, or actions involving "ball"

    oai_token-act-pair · gpt-3.5-turbo

    words that denote dominance or control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WD
    -0.71
     Inquis
    -0.65
    requires
    -0.62
    ahime
    -0.61
    yll
    -0.61
    advertising
    -0.59
    NPR
    -0.57
    ULE
    -0.57
     kindred
    -0.56
     Neighbor
    -0.55
    POSITIVE LOGITS
    zona
    0.82
    ophon
    0.71
    aneers
    0.67
    ardless
    0.67
    ioned
    0.65
    razil
    0.65
     fluids
    0.64
    estyles
    0.63
    à¦
    0.63
    halla
    0.63
    Activations Density 0.215%

    No Known Activations