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. 8-RES-JB
    6. 22804
    Prev
    Next
    INDEX
    Explanations

    gene-related terms and biological processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to genetic expression and biological processes

    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
     lounge
    -0.92
     Manor
    -0.79
     stew
    -0.78
     Rebels
    -0.78
     Hardcore
    -0.77
     specials
    -0.77
    Arcade
    -0.75
     Bunny
    -0.73
     blackmail
    -0.73
     Mayhem
    -0.73
    POSITIVE LOGITS
    ascular
    1.13
    âĢIJ
    1.10
    olar
    1.09
    oxic
    1.09
    phen
    1.08
    llular
    1.07
    ocy
    1.06
    ox
    1.04
    ogenic
    1.02
    otyp
    1.01
    Activations Density 0.366%

    No Known Activations