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. 6-RES-JB
    6. 3182
    Prev
    Next
    INDEX
    Explanations

    words related to methane, a compound stored in specific conditions and released under certain circumstances

    oai_token-act-pair · gpt-3.5-turbo

    mentions of methane and its related context in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ournal
    -1.02
    enegger
    -0.94
    angers
    -0.78
    fighters
    -0.76
    staff
    -0.75
    warts
    -0.75
    lass
    -0.74
    ings
    -0.74
    mx
    -0.73
    ymes
    -0.73
    POSITIVE LOGITS
    ©¶æ¥µ
    0.76
    rolet
    0.75
    CHA
    0.71
     methane
    0.66
     captcha
    0.64
    ilon
    0.63
     Hots
    0.62
    cha
    0.62
    isol
    0.61
    LV
    0.61
    Activations Density 0.060%

    No Known Activations