© 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. 13667
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions and decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate significant statements, actions, or conditions in a socio-political context

    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
    farious
    -0.57
    senal
    -0.54
     Saying
    -0.52
    laugh
    -0.50
    dding
    -0.49
    ullivan
    -0.49
    untled
    -0.48
    ULL
    -0.46
     Seym
    -0.46
     srf
    -0.46
    POSITIVE LOGITS
     is
    1.50
     isn
    1.39
     differs
    1.35
     belongs
    1.35
     consists
    1.34
     exists
    1.34
     involves
    1.33
     tends
    1.33
     depends
    1.32
     has
    1.32
    Activations Density 1.019%

    No Known Activations