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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 1274
    Prev
    Next
    INDEX
    Explanations

    terms related to fossil fuels

    oai_token-act-pair · gpt-3.5-turbo

    references to fossil fuels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    annis
    -0.79
    yang
    -0.76
    ansky
    -0.73
    ournal
    -0.73
    OA
    -0.72
    pace
    -0.71
    amber
    -0.70
    arta
    -0.68
    tub
    -0.67
    urat
    -0.67
    POSITIVE LOGITS
     fuels
    1.22
     fuel
    1.10
    ized
    1.10
    ization
    0.93
    fuel
    0.89
    izers
    0.86
    ised
    0.86
    ifer
    0.85
     fossil
    0.85
    itionally
    0.82
    Activations Density 0.017%

    No Known Activations