© 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. 6-RES-JB
    11. 13696
    Prev
    Next
    INDEX
    Explanations

    phrases related to continuing or persisting with an activity or situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include "carry on" or similar continuous actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ij士
    -0.74
     Nebula
    -0.69
    enegger
    -0.69
    Apps
    -0.68
    YP
    -0.68
    ocene
    -0.64
     Electoral
    -0.62
    OTUS
    -0.62
    RESULTS
    -0.62
    FACE
    -0.62
    POSITIVE LOGITS
    shore
    0.89
    rir
    0.79
     hemor
    0.74
     behalf
    0.74
     playback
    0.72
    slaught
    0.71
    ework
    0.70
    uph
    0.69
     misunder
    0.69
     uninterrupted
    0.68
    Activations Density 0.043%

    No Known Activations