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. 5-RES-JB
    6. 2205
    Prev
    Next
    INDEX
    Explanations

    oxygen-related terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to oxygen and its significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awar
    -0.86
    enegger
    -0.82
    erers
    -0.74
    things
    -0.73
    dar
    -0.73
    ORN
    -0.71
    invoke
    -0.71
    ochet
    -0.69
     Judgment
    -0.68
    REC
    -0.65
    POSITIVE LOGITS
     isot
    0.96
     oxygen
    0.95
     dioxide
    0.89
    toc
    0.87
     oxide
    0.87
     saturation
    0.85
     molecule
    0.83
    ated
    0.83
    uria
    0.80
     sulf
    0.79
    Activations Density 0.017%

    No Known Activations