© 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. 11-RES-JB
    11. 16394
    Prev
    Next
    INDEX
    Explanations

    verbs related to growth or advancement

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "rise" and its conjugations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Portal
    -0.68
    zos
    -0.64
    cise
    -0.62
     Shell
    -0.61
    DCS
    -0.59
    oured
    -0.59
    ciating
    -0.58
     Stores
    -0.57
    mination
    -0.57
     CLSID
    -0.57
    POSITIVE LOGITS
     Above
    0.95
     above
    0.92
     tide
    0.87
     perpend
    0.82
     tides
    0.79
     steadily
    0.78
    rising
    0.76
     up
    0.74
     stairs
    0.74
    ceed
    0.74
    Activations Density 0.069%

    No Known Activations