© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18924
    Prev
    Next
    INDEX
    Explanations

    financial transactions and amounts

    oai_token-act-pair · gpt-3.5-turbo

    financial transactions and amounts

    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
     occupant
    -0.64
    Introduced
    -0.62
    iferation
    -0.62
     transporter
    -0.61
    arth
    -0.60
    atto
    -0.58
     rollout
    -0.58
    NetMessage
    -0.58
     organism
    -0.58
     parade
    -0.57
    POSITIVE LOGITS
     âĤ¬
    1.89
     £
    1.88
     $
    1.87
     Rs
    1.75
     ¥
    1.70
    $
    1.65
    £
    1.61
     $$
    1.48
    .$
    1.40
     money
    1.39
    Activations Density 0.622%

    No Known Activations