© 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. 10-RES-JB
    11. 6570
    Prev
    Next
    INDEX
    Explanations

    words related to certainty and emphasis

    oai_token-act-pair · gpt-3.5-turbo

    expressions that indicate clarification or emphasis, particularly using phrases like "of course" and "in fact."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prus
    -0.67
     pione
    -0.64
     \'
    -0.62
     oun
    -0.60
    inki
    -0.60
    ategory
    -0.60
    krit
    -0.59
    ailability
    -0.59
    kefeller
    -0.59
     Doodle
    -0.58
    POSITIVE LOGITS
    ,
    1.00
    ,,
    0.88
    ,.
    0.81
    oret
    0.77
    *,
    0.77
    .,
    0.69
    )
    0.67
     anyway
    0.65
    ,-
    0.64
     anyways
    0.62
    Activations Density 0.107%

    No Known Activations