© 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. 2475
    Prev
    Next
    INDEX
    Explanations

    phrases relating to newsletter subscription and promotional messaging

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

    mentions of a source or origin in text

    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
     tremend
    -0.81
     obser
    -0.80
     exting
    -0.76
     seiz
    -0.75
     destro
    -0.74
     arrang
    -0.72
    onge
    -0.69
     stopp
    -0.66
     estab
    -0.65
    VIDIA
    -0.64
    POSITIVE LOGITS
     The
    1.02
     POLITICO
    0.82
     CrossRef
    0.69
    The
    0.68
    Trend
    0.67
    BC
    0.67
     Gow
    0.66
     Cycling
    0.64
     Dupl
    0.64
    Microsoft
    0.64
    Activations Density 0.013%

    No Known Activations