© 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. 9-RES-JB
    11. 18292
    Prev
    Next
    INDEX
    Explanations

    phrases indicating high likelihood or possibility of something happening

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating probability or likelihood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.72
    feeding
    -0.66
    iful
    -0.64
    CLASSIFIED
    -0.62
    eworthy
    -0.61
     Columb
    -0.60
    fighting
    -0.59
     Mour
    -0.58
    cussion
    -0.58
    Trivia
    -0.58
    POSITIVE LOGITS
     be
    1.09
     become
    1.03
     explode
    0.98
     prove
    0.95
     have
    0.93
     succeed
    0.92
     lose
    0.90
     revert
    0.90
     regress
    0.90
     reside
    0.89
    Activations Density 0.071%

    No Known Activations