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. 8-RES-JB
    6. 19833
    Prev
    Next
    INDEX
    Explanations

    terms related to life forms, especially in the context of scientific exploration and study

    oai_token-act-pair · gpt-3.5-turbo

    references to life forms and the conditions necessary for life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ´ãĤ¡
    -0.78
    EStreamFrame
    -0.77
    DCS
    -0.76
    åĭ
    -0.76
    udeb
    -0.68
    76561
    -0.65
     Mall
    -0.65
     cuff
    -0.65
     Buckingham
    -0.64
    iku
    -0.63
    POSITIVE LOGITS
     organisms
    1.13
    forms
    1.01
    brates
    0.97
    worms
    0.97
     extrater
    0.94
     organism
    0.91
     species
    0.90
     microbes
    0.88
    fish
    0.87
     inhab
    0.84
    Activations Density 0.072%

    No Known Activations