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. 9-RES-JB
    6. 630
    Prev
    Next
    INDEX
    Explanations

    instances of words related to bio/medical terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of biological or biotechnological terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atche
    -0.80
    xual
    -0.71
    bilt
    -0.68
    ĪĴ
    -0.63
    ĸļ
    -0.63
    earch
    -0.62
     Jagu
    -0.60
    claw
    -0.59
    tty
    -0.58
    cheat
    -0.58
    POSITIVE LOGITS
    é¾įå
    0.74
    icable
    0.71
    ritz
    0.66
    arten
    0.65
    anni
    0.65
    entric
    0.62
    pas
    0.61
    vernment
    0.61
    rical
    0.61
    ratulations
    0.60
    Activations Density 0.267%

    No Known Activations