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. 10-RES-JB
    6. 11907
    Prev
    Next
    INDEX
    Explanations

    names or entities related to people

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ge" as well as related terms or patterns representing age

    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
    kefeller
    -0.77
    Interstitial
    -0.69
    rontal
    -0.66
    icum
    -0.65
    TEXT
    -0.63
    iqueness
    -0.63
     ABE
    -0.62
    ework
    -0.62
    ishment
    -0.59
    INC
    -0.58
    POSITIVE LOGITS
    hog
    1.28
    rer
    1.24
    orge
    1.19
    rers
    1.12
    ll
    1.12
    cko
    1.03
    vity
    1.02
    llers
    0.97
    orget
    0.97
    eks
    0.95
    Activations Density 0.038%

    No Known Activations