© 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. 9-RES-JB
    11. 18586
    Prev
    Next
    INDEX
    Explanations

    words related to quantities or descriptions of large amounts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express quantity, particularly involving the word "all" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elist
    -0.86
    etus
    -0.80
    IER
    -0.72
    atively
    -0.71
    quet
    -0.71
    emale
    -0.71
    ħĭ
    -0.71
    ebin
    -0.70
    elfth
    -0.70
    Ö¼
    -0.69
    POSITIVE LOGITS
     fuss
    1.09
     hype
    1.08
     hoop
    1.06
     negativity
    0.97
     twists
    0.95
     shenanigans
    0.92
     horrors
    0.91
     pomp
    0.91
     accol
    0.90
     talk
    0.87
    Activations Density 0.102%

    No Known Activations