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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 23515
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to a specific word containing "row"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "row" followed by numeric values or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nomine
    -0.90
     mosqu
    -0.89
    £ı
    -0.87
     metic
    -0.86
    urated
    -0.82
     mathemat
    -0.71
     flaw
    -0.70
     incent
    -0.70
     improbable
    -0.69
     unnecess
    -0.68
    POSITIVE LOGITS
    row
    1.19
    restling
    1.15
    dy
    0.98
    ski
    0.96
    icz
    0.92
    ars
    0.91
    atts
    0.86
    agy
    0.85
    lings
    0.85
    rows
    0.84
    Activations Density 0.006%

    No Known Activations