© 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. 6-RES-JB
    11. 11849
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a large quantity or amount

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating abundance or a high quantity of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ufact
    -0.91
    buster
    -0.81
    merce
    -0.78
    ilk
    -0.77
    breakers
    -0.76
    hammad
    -0.75
    breaker
    -0.73
    _-
    -0.71
    makes
    -0.71
    cedes
    -0.68
    POSITIVE LOGITS
     overlap
    0.97
     similarities
    0.90
     disagreement
    0.79
     appetite
    0.77
     chance
    0.75
     vacancies
    0.75
     difference
    0.74
     differences
    0.74
     shortage
    0.73
     heterogeneity
    0.73
    Activations Density 0.094%

    No Known Activations