© 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. 7-RES-JB
    11. 20805
    Prev
    Next
    INDEX
    Explanations

    instances where something or someone fits a particular description or criteria

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to fitting or conforming to standards or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ£
    -0.79
    aler
    -0.71
    ilant
    -0.71
    usted
    -0.69
    lling
    -0.64
    iger
    -0.62
    peer
    -0.59
    gov
    -0.59
    myra
    -0.56
     recovering
    -0.56
    POSITIVE LOGITS
     precon
    0.98
     snug
    0.95
     bounds
    0.89
     neatly
    0.83
     niche
    0.82
     stereotype
    0.80
     mold
    0.78
     criteria
    0.77
     mould
    0.76
    Square
    0.75
    Activations Density 0.113%

    No Known Activations