© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20309
    Prev
    Next
    INDEX
    Explanations

    phrases or statements expressing uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express uncertainty or questioning of certainty

    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
    Bloomberg
    -0.60
    yip
    -0.56
    portation
    -0.53
     Dangerous
    -0.53
     Diary
    -0.51
    uler
    -0.51
    ticket
    -0.50
    Land
    -0.50
    KK
    -0.50
    issance
    -0.50
    POSITIVE LOGITS
     sure
    1.21
     yourselves
    1.03
     yourself
    0.95
     instance
    0.95
     certain
    0.93
     oneself
    0.92
     ourselves
    0.88
     Yourself
    0.86
    see
    0.86
     example
    0.85
    Activations Density 0.091%

    No Known Activations