© 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. 9-RES-JB
    11. 5511
    Prev
    Next
    INDEX
    Explanations

    economic terms and statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to financial statistics and economic conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ħ¢
    -0.65
    ortment
    -0.62
     fitness
    -0.61
    enery
    -0.61
    values
    -0.60
     reinforcement
    -0.59
     anonymity
    -0.59
    ighting
    -0.59
    rities
    -0.59
     styling
    -0.59
    POSITIVE LOGITS
     compared
    0.94
     whereas
    0.87
    /.
    0.81
     multiplied
    0.76
     Compare
    0.76
    Compare
    0.74
    *.
    0.73
     divided
    0.71
     versus
    0.71
     minus
    0.68
    Activations Density 0.245%

    No Known Activations