© 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. 8-RES-JB
    11. 14141
    Prev
    Next
    INDEX
    Explanations

    the word "tell" accompanied by descriptions or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to perception and communication of information

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ItemTracker
    -0.78
    pmwiki
    -0.75
    Contents
    -0.70
    zinski
    -0.69
    urdue
    -0.69
    elsh
    -0.67
    rane
    -0.64
    igham
    -0.63
    Kin
    -0.63
    imposed
    -0.61
    POSITIVE LOGITS
    tale
    1.19
    ingly
    0.86
     us
    0.69
    tell
    0.69
    ariat
    0.68
    eret
    0.66
     apart
    0.65
    itudinal
    0.62
    away
    0.61
     lies
    0.60
    Activations Density 0.025%

    No Known Activations