© 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. 12582
    Prev
    Next
    INDEX
    Explanations

    currency amounts

    oai_token-act-pair · gpt-3.5-turbo

    currency amounts and financial figures

    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
     Tall
    -0.76
    ographed
    -0.75
     Ital
    -0.70
     Lub
    -0.70
     Bru
    -0.68
     Advent
    -0.68
     Dill
    -0.66
     Fra
    -0.66
    ifest
    -0.66
     Springfield
    -0.65
    POSITIVE LOGITS
    £
    1.50
     £
    1.05
    ©¶æ¥µ
    0.97
     (£
    0.92
    USD
    0.91
    $
    0.88
    /$
    0.87
    âĤ¬
    0.80
    $$
    0.80
     âĤ¬
    0.79
    Activations Density 0.010%

    No Known Activations