© 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. 10-RES-JB
    11. 20677
    Prev
    Next
    INDEX
    Explanations

    large monetary figures mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    large monetary values and financial contributions

    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
    ãĥ¤
    -0.71
    cknow
    -0.65
    ãĤ¦ãĤ¹
    -0.58
    umbn
    -0.56
    natureconservancy
    -0.53
    eworld
    -0.52
    asser
    -0.52
     Situation
    -0.52
    aple
    -0.51
    anwhile
    -0.50
    POSITIVE LOGITS
     (£
    1.05
     dollars
    0.99
     worth
    0.98
     annually
    0.94
     USD
    0.91
     towards
    0.79
     pounds
    0.79
     toward
    0.78
     Dollars
    0.77
    aires
    0.75
    Activations Density 0.150%

    No Known Activations