© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 11621
    Prev
    Next
    INDEX
    Explanations

    Bipartite names with the letter 'A' followed by 'k'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Ak" in various contexts

    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
     Hurricanes
    -0.71
     Crescent
    -0.67
    ++++
    -0.62
     Reaper
    -0.60
     Founders
    -0.57
    ATIONAL
    -0.56
     formerly
    -0.56
     unauthorized
    -0.56
     sorts
    -0.55
    åĤ
    -0.55
    POSITIVE LOGITS
    htar
    1.22
    atsuki
    1.15
    adem
    1.11
    uma
    0.99
    unin
    0.98
    iba
    0.97
    ansas
    0.97
    alon
    0.93
    imoto
    0.93
    amaru
    0.92
    Activations Density 0.021%

    No Known Activations