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

    Neuronpedia

    Jacobian LensNEW
    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. 3243
    Prev
    Next
    INDEX
    Explanations

    phrases expressing curiosity or investigation

    oai_token-act-pair · gpt-3.5-turbo

    instances of curiosity and references to change or transformation

    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
    lement
    -0.69
    Forge
    -0.66
    mentioned
    -0.63
    Issue
    -0.62
    mania
    -0.61
    marine
    -0.60
    elsen
    -0.60
    illon
    -0.60
     DEFENSE
    -0.58
    abase
    -0.58
    POSITIVE LOGITS
     so
    1.67
    so
    1.56
     SO
    1.30
     So
    1.20
    So
    1.15
     such
    1.07
    SO
    1.05
    such
    0.96
     cumbers
    0.74
     yet
    0.72
    Activations Density 0.119%

    No Known Activations