© 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. 10230
    Prev
    Next
    INDEX
    Explanations

    numerical facts related to various events or statistics

    oai_token-act-pair · gpt-3.5-turbo

    statistics related to deaths or serious incidents

    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
    DOS
    -0.62
    ega
    -0.61
    issan
    -0.61
    itimate
    -0.60
    Nut
    -0.60
    lishes
    -0.59
    rious
    -0.59
    pn
    -0.58
    ocative
    -0.56
     Dalai
    -0.55
    POSITIVE LOGITS
     annually
    1.27
     alone
    1.20
     compared
    1.11
     apiece
    1.03
     each
    1.01
     yearly
    0.98
     excluding
    0.94
     (£
    0.88
     during
    0.88
     every
    0.87
    Activations Density 0.492%

    No Known Activations