© 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. 1450
    Prev
    Next
    INDEX
    Explanations

    words related to certainty or emphasis, such as "Absolutely"

    oai_token-act-pair · gpt-3.5-turbo

    affirmative statements or expressions of certainty

    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
     stub
    -0.62
     weeds
    -0.58
     status
    -0.57
     delinqu
    -0.57
    ger
    -0.55
     quarters
    -0.55
     reorgan
    -0.53
    chan
    -0.52
     shuffle
    -0.52
    /(
    -0.52
    POSITIVE LOGITS
     Absolutely
    2.99
    Absolutely
    2.93
    absolutely
    2.48
     absolutely
    1.80
     Definitely
    1.50
     Totally
    1.38
    YES
    1.23
     utterly
    1.17
    extremely
    1.12
    completely
    1.12
    Activations Density 0.020%

    No Known Activations