© 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. 10906
    Prev
    Next
    INDEX
    Explanations

    expressions of numerical comparison pertaining to quantities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express comparative quantities or multipliers

    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
    Reviewer
    -0.93
    aceous
    -0.93
    liction
    -0.85
    ourt
    -0.77
    arty
    -0.76
    ists
    -0.75
    OST
    -0.73
    ged
    -0.70
    igans
    -0.70
    orts
    -0.70
    POSITIVE LOGITS
    cale
    0.87
     consecut
    0.81
    paces
    0.69
     gestation
    0.69
    pan
    0.66
    fold
    0.65
    bps
    0.63
     fold
    0.63
    cens
    0.63
     per
    0.63
    Activations Density 0.024%

    No Known Activations