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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-RES-JB
    6. 5731
    Prev
    Next
    INDEX
    Explanations

    mentions of the chemical element sulfur

    oai_token-act-pair · gpt-3.5-turbo

    references to sulfur and its related contexts

    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
    nut
    -0.77
    jer
    -0.76
    tops
    -0.75
    aiman
    -0.74
    obar
    -0.73
    ocular
    -0.72
    rypt
    -0.71
    hire
    -0.70
    ridges
    -0.70
    aith
    -0.70
    POSITIVE LOGITS
     ANGEL
    0.78
    mble
    0.77
    xual
    0.74
    geist
    0.72
    ited
    0.71
     IPM
    0.70
     charact
    0.67
    Ô
    0.66
    itism
    0.66
    orgetown
    0.65
    Activations Density 0.057%

    No Known Activations