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. 2-RES-JB
    6. 13270
    Prev
    Next
    INDEX
    Explanations

    mentions of ice skaters or skating

    oai_token-act-pair · gpt-3.5-turbo

    references to skateboarding or related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mayweather
    -0.76
     Cause
    -0.65
     vengeance
    -0.63
     Manson
    -0.63
     Tud
    -0.62
    terday
    -0.62
     Geo
    -0.62
    hibition
    -0.61
     resentment
    -0.60
     patriarchal
    -0.60
    POSITIVE LOGITS
    yrim
    1.17
    ipper
    1.02
     sk
    1.02
    IPP
    0.99
    ipped
    0.94
    ippers
    0.94
    ipp
    0.94
    oop
    0.92
    ull
    0.92
    irts
    0.92
    Activations Density 0.006%

    No Known Activations