© 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. 2744
    Prev
    Next
    INDEX
    Explanations

    numeric values related to worth, estimation, and cost

    oai_token-act-pair · gpt-3.5-turbo

    expressions of financial value or worth

    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
    Interstitial
    -0.65
    sburg
    -0.65
    clus
    -0.64
    unction
    -0.63
    rete
    -0.62
    ador
    -0.62
    milo
    -0.62
    avier
    -0.61
    itation
    -0.60
    onel
    -0.60
    POSITIVE LOGITS
     $
    1.37
     âĤ¬
    1.31
     Rs
    1.26
     £
    1.21
     USD
    1.19
     ¥
    1.19
    $
    1.17
     HK
    1.10
     EUR
    1.09
     "$
    1.03
    Activations Density 0.163%

    No Known Activations