© 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. 10094
    Prev
    Next
    INDEX
    Explanations

    instances where actions or responsibilities are being taken seriously

    oai_token-act-pair · gpt-3.5-turbo

    references to responsibilities, concerns, and issues

    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
    etheless
    -0.80
    entimes
    -0.65
     accompanies
    -0.64
    furt
    -0.61
    los
    -0.60
    ITNESS
    -0.60
    izabeth
    -0.59
    whose
    -0.57
    DA
    -0.55
    nor
    -0.55
    POSITIVE LOGITS
     squarely
    0.91
     aside
    0.86
     down
    0.82
     into
    0.81
     overboard
    0.81
     seriously
    0.75
     intact
    0.74
     onto
    0.73
     firmly
    0.72
     forward
    0.72
    Activations Density 0.204%

    No Known Activations