© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18463
    Prev
    Next
    INDEX
    Explanations

    terms related to technology, finance, and proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    that relate to organizations or entities involved in significant transactions or environmental impacts

    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
    "},"
    -0.65
     eternity
    -0.62
     attm
    -0.62
     Grateful
    -0.56
    blocking
    -0.55
     contacting
    -0.54
    "]=>
    -0.53
    rather
    -0.53
     Authorization
    -0.53
     Shutterstock
    -0.53
    POSITIVE LOGITS
     likewise
    1.11
     fared
    1.07
     meanwhile
    0.97
     went
    0.92
     gave
    0.92
     has
    0.86
     took
    0.86
     did
    0.85
     is
    0.85
     contributes
    0.84
    Activations Density 0.467%

    No Known Activations