© 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. 2305
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions or the finance industry

    oai_token-act-pair · gpt-3.5-turbo

    generic punctuation marks, specifically periods

    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
     barg
    -0.69
     creeping
    -0.65
     Elise
    -0.63
     accelerating
    -0.61
     preventive
    -0.60
     ped
    -0.60
     corner
    -0.59
     babe
    -0.59
     unders
    -0.59
     unle
    -0.59
    POSITIVE LOGITS
    NET
    1.35
    _.
    1.19
    -.
    1.14
    gif
    1.10
    mobi
    1.04
    pdf
    1.04
    Pa
    1.03
    aspx
    0.98
    hack
    0.98
    wav
    0.98
    Activations Density 0.041%

    No Known Activations