© 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. 2-RES-JB
    11. 5328
    Prev
    Next
    INDEX
    Explanations

    cautious or timid language

    oai_token-act-pair · gpt-3.5-turbo

    expressions describing caution and hesitance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    frey
    -0.79
    LAN
    -0.77
    mpeg
    -0.77
    bleacher
    -0.77
    plex
    -0.75
    tein
    -0.74
    Plex
    -0.73
    intern
    -0.72
    Tube
    -0.72
    bsite
    -0.71
    POSITIVE LOGITS
     optimism
    1.12
     cautious
    1.03
     optimistic
    0.96
     caution
    0.93
     precaution
    0.88
     adolesc
    0.88
     approach
    0.87
     equilibrium
    0.82
     hesitation
    0.81
     minded
    0.81
    Activations Density 0.012%

    No Known Activations