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. 0-RES-JB
    6. 23507
    Prev
    Next
    INDEX
    Explanations

    embryo-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to embryos and related concepts in biological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gab
    -0.78
     Grizzlies
    -0.77
    liga
    -0.75
    Trend
    -0.75
     Dud
    -0.71
     Nas
    -0.70
     Norm
    -0.70
     Blazers
    -0.70
     Charg
    -0.68
     Gas
    -0.68
    POSITIVE LOGITS
     embryos
    2.09
     Skywalker
    1.86
     embryo
    1.83
    Sky
    1.47
     embryonic
    1.44
     Kenobi
    1.29
     miniature
    1.29
    aan
    1.25
     Typhoon
    1.13
     {\
    1.12
    Activations Density 0.057%

    No Known Activations