© 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. 7-RES-JB
    11. 12448
    Prev
    Next
    INDEX
    Explanations

    the word "won"

    oai_token-act-pair · gpt-3.5-turbo

    negations or instances of "won't."

    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
    gypt
    -0.71
    eki
    -0.63
    illin
    -0.62
    OTOS
    -0.61
    Factor
    -0.60
     periphery
    -0.60
     Traps
    -0.59
    bian
    -0.58
     compr
    -0.57
     constrained
    -0.57
    POSITIVE LOGITS
    't
    1.43
    itive
    1.08
    cest
    0.95
    now
    0.94
    iors
    0.85
    geon
    0.83
    ced
    0.82
    ests
    0.81
    ipeg
    0.81
    cing
    0.81
    Activations Density 0.036%

    No Known Activations