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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 14237
    Prev
    Next
    INDEX
    Explanations

    keywords related to motorsports

    oai_token-act-pair · gpt-3.5-turbo

    references to motor sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mind
    -0.73
     Homo
    -0.67
     sheet
    -0.67
     resh
    -0.66
     Shining
    -0.64
     inh
    -0.64
     prayer
    -0.63
     stain
    -0.63
     brainstorm
    -0.62
     spoon
    -0.62
    POSITIVE LOGITS
    ports
    4.90
    port
    2.70
    porting
    2.67
    ported
    2.33
    PORT
    2.01
    porter
    1.74
    portation
    1.62
    por
    1.50
    ORTS
    1.35
     Ports
    1.33
    Activations Density 0.008%

    No Known Activations