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. 11-RES-JB
    6. 8376
    Prev
    Next
    INDEX
    Explanations

    mention of sports teams or events in a context of fan enthusiasm

    oai_token-act-pair · gpt-3.5-turbo

    specific numbers or sequences that indicate order or ranking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tram
    -0.84
     confir
    -0.82
     counselling
    -0.77
     enqu
    -0.75
     stressed
    -0.75
     probation
    -0.74
     vain
    -0.74
     preservation
    -0.73
     citiz
    -0.73
     redes
    -0.73
    POSITIVE LOGITS
    advertising
    1.88
    Probably
    1.63
    Another
    1.59
    This
    1.56
    Sometimes
    1.54
    Located
    1.54
    Okay
    1.53
    Constructed
    1.53
    Similar
    1.49
    Perhaps
    1.48
    Activations Density 0.168%

    No Known Activations