© 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. 8-RES-JB
    11. 2589
    Prev
    Next
    INDEX
    Explanations

    phrases indicating continuity or persistence

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to persistence or ongoing existence

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    buster
    -0.62
    strip
    -0.58
     pounded
    -0.56
     |--
    -0.55
    achi
    -0.55
    hower
    -0.54
    icles
    -0.54
     chast
    -0.54
     closely
    -0.54
     princip
    -0.53
    POSITIVE LOGITS
     plenty
    1.00
     ample
    0.83
     lots
    0.80
    omething
    0.77
     unanim
    0.75
    umption
    0.74
     alot
    0.70
     precedent
    0.70
    enough
    0.70
     enough
    0.69
    Activations Density 0.104%

    No Known Activations