© 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. 3-RES-JB
    11. 23028
    Prev
    Next
    INDEX
    Explanations

    multimillionaires and related words

    oai_token-act-pair · gpt-3.5-turbo

    references to monetary amounts and financial concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.98
    Downloadha
    -0.77
    liness
    -0.69
    æѦ
    -0.64
     resp
    -0.64
    ç«
    -0.64
    REDACTED
    -0.64
    Thumbnail
    -0.63
    erness
    -0.62
     Verse
    -0.62
    POSITIVE LOGITS
    ple
    1.27
    agine
    1.03
    pton
    1.01
    plement
    0.99
    illion
    0.96
    puter
    0.91
    unicip
    0.90
    resent
    0.89
    iple
    0.87
    ply
    0.86
    Activations Density 0.013%

    No Known Activations