© 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. 10-RES-JB
    11. 15984
    Prev
    Next
    INDEX
    Explanations

    financial figures and amounts

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to financial statistics and economic figures

    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
    antine
    -0.63
     buddies
    -0.57
     comrade
    -0.57
    aciously
    -0.57
     whistle
    -0.57
     anonymity
    -0.57
     inaction
    -0.56
     favorites
    -0.54
     reinforcement
    -0.54
     instinct
    -0.54
    POSITIVE LOGITS
     compared
    1.01
     whereas
    0.83
    /,
    0.79
     versus
    0.78
    /.
    0.76
     vs
    0.75
     (-
    0.75
    ross
    0.74
    last
    0.73
     excluding
    0.71
    Activations Density 0.155%

    No Known Activations