© 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. 8-RES-JB
    11. 7817
    Prev
    Next
    INDEX
    Explanations

    phrases related to confidence in the future

    oai_token-act-pair · gpt-3.5-turbo

    expressions of future expectations or predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.75
     Radius
    -0.66
    ancer
    -0.66
    aina
    -0.65
    Lear
    -0.64
    arthed
    -0.63
     adolesc
    -0.62
    olis
    -0.62
     Strategy
    -0.61
    maps
    -0.60
    POSITIVE LOGITS
     someday
    1.20
     be
    1.20
     eventually
    1.12
     continue
    1.10
     succeed
    1.01
     prevail
    0.97
     become
    0.93
     inevitably
    0.93
     emerge
    0.93
     remain
    0.91
    Activations Density 0.179%

    No Known Activations