© 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. 1-RES-JB
    11. 5399
    Prev
    Next
    INDEX
    Explanations

    phrases expressing speculation or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    expressions of speculation or conjecture

    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
    ammy
    -0.85
    assic
    -0.71
    League
    -0.70
    Sharp
    -0.69
    taboola
    -0.66
    Cook
    -0.66
    æĸ¹
    -0.66
    Blu
    -0.66
    Tips
    -0.65
    andals
    -0.65
    POSITIVE LOGITS
     suppose
    1.06
     guess
    0.87
     imagine
    0.84
    agine
    0.83
     assume
    0.80
     hypot
    0.80
     presume
    0.79
    inois
    0.78
     Leilan
    0.74
     assum
    0.73
    Activations Density 0.009%

    No Known Activations