© 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. 0-RES-JB
    11. 20179
    Prev
    Next
    INDEX
    Explanations

    the word "passing" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "passing" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olit
    -0.86
    conom
    -0.83
    UFF
    -0.66
    mbudsman
    -0.65
    mega
    -0.64
    olitics
    -0.64
    ibl
    -0.64
    encia
    -0.63
    ruit
    -0.62
    OME
    -0.62
    POSITIVE LOGITS
     passing
    3.91
     Passing
    2.48
     pass
    1.95
     passes
    1.88
     passed
    1.79
    pass
    1.66
     passage
    1.55
    Pass
    1.52
     passer
    1.48
     passers
    1.46
    Activations Density 0.015%

    No Known Activations