© 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. 4349
    Prev
    Next
    INDEX
    Explanations

    phrases indicating compatibility or fitting well together

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to compatibility and effectiveness in relationships or comparisons

    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
    ittance
    -0.72
    ithing
    -0.69
    arthed
    -0.63
    ewitness
    -0.63
    uploads
    -0.62
    oldown
    -0.62
    rez
    -0.60
    Winged
    -0.58
    tein
    -0.58
    ibi
    -0.58
    POSITIVE LOGITS
     nicely
    1.77
     better
    1.68
     poorly
    1.67
     perfectly
    1.65
     well
    1.65
     beautifully
    1.61
     brilliantly
    1.49
     wonderfully
    1.48
     best
    1.41
     differently
    1.40
    Activations Density 0.711%

    No Known Activations