© 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. 3214
    Prev
    Next
    INDEX
    Explanations

    phrases related to testing and deployment in various environments

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to testing and evaluation in challenging conditions

    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
     heirs
    -0.80
    $$$$
    -0.76
     dues
    -0.73
    unless
    -0.72
     condol
    -0.70
     excuses
    -0.69
    Whoever
    -0.68
    want
    -0.67
     gravy
    -0.65
     heir
    -0.64
    POSITIVE LOGITS
     test
    1.44
     simulated
    1.41
     tests
    1.38
     testing
    1.37
     experiment
    1.36
     simulations
    1.36
     prototypes
    1.32
    tests
    1.31
     demo
    1.31
     experiments
    1.30
    Activations Density 0.692%

    No Known Activations