© 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. 18641
    Prev
    Next
    INDEX
    Explanations

    words related to education and teaching

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to education and awareness of historical events

    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
     eleph
    -0.67
    accompan
    -0.66
    raq
    -0.63
     neighb
    -0.63
     helicop
    -0.59
    ratulations
    -0.58
    achy
    -0.55
    HAM
    -0.54
    Ba
    -0.54
     PA
    -0.54
    POSITIVE LOGITS
     the
    0.77
    the
    0.69
    Õ
    0.69
    ÑĮ
    0.68
    ust
    0.62
    UAL
    0.61
     tha
    0.56
    SpaceEngineers
    0.55
    usted
    0.55
    rontal
    0.55
    Activations Density 0.072%

    No Known Activations