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. 9-RES-JB
    6. 14661
    Prev
    Next
    INDEX
    Explanations

    mentions of numbers and measurements

    oai_token-act-pair · gpt-3.5-turbo

    mentions of educational institutions and their activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interstellar
    -0.73
     IMAGES
    -0.73
    ortal
    -0.70
    obin
    -0.68
    etimes
    -0.68
     vanquished
    -0.67
    ilan
    -0.67
    Austral
    -0.67
    redo
    -0.66
    verse
    -0.66
    POSITIVE LOGITS
     reopened
    0.94
     staffed
    0.84
     ordinances
    0.82
     renovation
    0.79
     superintendent
    0.78
     lockdown
    0.77
     accommodating
    0.76
     catering
    0.76
     renovations
    0.75
     housed
    0.75
    Activations Density 0.630%

    No Known Activations