© 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. 6-RES-JB
    11. 17824
    Prev
    Next
    INDEX
    Explanations

    names and possibly discussions between individuals, as well as references to courts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     respectively
    -0.69
    chery
    -0.68
     )]
    -0.68
    conservancy
    -0.63
    historic
    -0.61
     ),
    -0.61
     lately
    -0.61
    BuyableInstoreAndOnline
    -0.60
    bred
    -0.60
     gearing
    -0.59
    POSITIVE LOGITS
     laughs
    0.85
    ITNESS
    0.82
    ERY
    0.82
    laughter
    0.82
    ENE
    0.80
     laughed
    0.78
    laughs
    0.77
    ause
    0.77
    othy
    0.76
    miah
    0.75
    Activations Density 0.131%

    No Known Activations