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. 10-RES-JB
    6. 23195
    Prev
    Next
    INDEX
    Explanations

    fossils mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fossils and paleontological evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orney
    -0.83
    advertising
    -0.76
    License
    -0.73
    Rating
    -0.73
     PID
    -0.72
     discretionary
    -0.72
     lawy
    -0.69
     throttle
    -0.69
     Virtue
    -0.68
     malice
    -0.67
    POSITIVE LOGITS
     specimens
    1.46
     samples
    1.24
     specimen
    1.23
     genomes
    1.22
     fossils
    1.21
     fragments
    1.10
     genome
    1.08
     analysed
    1.06
     unearthed
    1.05
     excav
    1.03
    Activations Density 0.206%

    No Known Activations