© 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. 11-RES-JB
    11. 3409
    Prev
    Next
    INDEX
    Explanations

    financial numbers or amounts mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to financial figures and estimations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mination
    -0.68
    ador
    -0.68
    mund
    -0.64
     horizont
    -0.64
    dayName
    -0.63
     mosqu
    -0.63
    itions
    -0.60
    roma
    -0.60
     actionGroup
    -0.59
    acity
    -0.59
    POSITIVE LOGITS
     $
    1.65
     £
    1.48
     âĤ¬
    1.45
    $
    1.41
     Rs
    1.40
     USD
    1.35
     ¥
    1.25
     EUR
    1.17
     HK
    1.09
    £
    1.07
    Activations Density 0.101%

    No Known Activations