Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 14462
    Prev
    Next
    INDEX
    Explanations

    sports-related nouns, particularly those related to football

    oai_token-act-pair · gpt-3.5-turbo

    articles and indefinite articles used before nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    notes
    -0.79
    AIDS
    -0.71
     Observatory
    -0.71
    encies
    -0.70
    Edit
    -0.69
    coins
    -0.68
    ATURES
    -0.68
    achusetts
    -0.67
    ode
    -0.66
     workshops
    -0.65
    POSITIVE LOGITS
     terrific
    0.99
     whopping
    0.97
     slew
    0.96
     disappointing
    0.96
     resurg
    0.94
     lot
    0.91
     plethora
    0.91
     stellar
    0.88
     revamped
    0.88
     playoff
    0.88
    Activations Density 0.214%

    No Known Activations