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. 9-RES-JB
    6. 12135
    Prev
    Next
    INDEX
    Explanations

    words related to geographical terms and statistics

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data and statistics related to demographics and comparisons

    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
    umbn
    -0.74
    wcsstore
    -0.68
    .}
    -0.68
    udeb
    -0.67
    apixel
    -0.66
    emonic
    -0.64
    dylib
    -0.63
    osate
    -0.63
    flush
    -0.62
     Canaver
    -0.62
    POSITIVE LOGITS
    aurus
    0.73
     tends
    0.71
     stays
    0.70
     is
    0.70
     prefers
    0.69
     accordingly
    0.68
     likewise
    0.65
     responds
    0.65
     goes
    0.62
     contributes
    0.62
    Activations Density 0.289%

    No Known Activations