© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 4857
    Prev
    Next
    INDEX
    Explanations

    information related to taxes and financial tips

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    phrases suggesting recommendations or advice

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ELD
    -0.75
    ActionCode
    -0.74
    Ė
    -0.74
    ü
    -0.73
    ė
    -0.73
    Ğ
    -0.73
    oreAndOnline
    -0.73
    ø
    -0.73
    Đ
    -0.73
    ġ
    -0.73
    POSITIVE LOGITS
     bookmark
    1.02
     acquaint
    1.00
     consult
    0.98
     check
    0.96
     beware
    0.96
     heed
    0.93
     remember
    0.92
     ALWAYS
    0.91
     verify
    0.88
     note
    0.86
    Activations Density 0.182%

    No Known Activations