© 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. 4-RES-JB
    11. 15643
    Prev
    Next
    INDEX
    Explanations

    phrases associated with money or monetary units in their text

    oai_token-act-pair · gpt-3.5-turbo

    references to monetary concepts

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

    No Comments

    Negative Logits
     Norn
    -0.87
    éĹĺ
    -0.87
    OHN
    -0.84
    ULTS
    -0.82
    FUL
    -0.81
    æĸ¹
    -0.80
    IBLE
    -0.79
    ORTS
    -0.78
    INGTON
    -0.76
    EXP
    -0.75
    POSITIVE LOGITS
    stros
    1.27
    olithic
    1.16
    olith
    1.10
    soon
    1.04
    itored
    0.97
    ocular
    0.95
    ograph
    0.95
    ique
    0.94
    ero
    0.94
    oton
    0.93
    Activations Density 0.008%

    No Known Activations