Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 10126
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or skepticism

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to skepticism or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.91
    pmwiki
    -0.88
     Kinnikuman
    -0.78
    Interstitial
    -0.70
    region
    -0.66
    cycl
    -0.65
    Entry
    -0.63
    handle
    -0.63
    OW
    -0.63
    psc
    -0.62
    POSITIVE LOGITS
     doubts
    1.16
     suspicions
    0.80
    warts
    0.78
    afety
    0.73
     den
    0.72
     worries
    0.71
     doubted
    0.71
     stemmed
    0.70
    atisf
    0.70
     Ans
    0.69
    Activations Density 0.015%

    No Known Activations