© 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. 15391
    Prev
    Next
    INDEX
    Explanations

    places or situations where something fits in or is compatible

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a fitting or appropriate connection between concepts or situations

    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
    iger
    -0.75
    aler
    -0.71
    ãĥ£
    -0.70
    mares
    -0.67
    amaz
    -0.63
    icide
    -0.62
    xiety
    -0.62
    flush
    -0.61
    lling
    -0.60
    gov
    -0.60
    POSITIVE LOGITS
     precon
    0.89
     snug
    0.85
     bounds
    0.85
     stereotype
    0.80
    Square
    0.80
     niche
    0.78
    Interstitial
    0.76
     criteria
    0.74
     Slot
    0.74
     neatly
    0.72
    Activations Density 0.119%

    No Known Activations