© 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 EvalsExportsinterp-engineNEWAPI 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. 11409
    Prev
    Next
    INDEX
    Explanations

    phrases related to examining, checking, and reviewing for investigation or assessment purposes

    oai_token-act-pair · gpt-3.5-turbo

    references to commercial products, legal cases, and official investigations

    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
     hugs
    -0.74
    å§
    -0.62
    ario
    -0.62
     Shank
    -0.61
    Stretch
    -0.61
    udeb
    -0.61
    ¬¼
    -0.59
     Riding
    -0.59
    cott
    -0.59
     Stro
    -0.58
    POSITIVE LOGITS
     carefully
    1.13
     closely
    1.12
     objectively
    1.05
     thoroughly
    0.96
     favorably
    0.94
     differently
    0.93
     extensively
    0.92
     aloud
    0.92
     separately
    0.87
     diligently
    0.84
    Activations Density 0.591%

    No Known Activations