© 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. 22511
    Prev
    Next
    INDEX
    Explanations

    words related to physical changes or transformations

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to physical change or transformation

    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
    icz
    -0.84
    dding
    -0.78
    uning
    -0.72
    insk
    -0.69
    anya
    -0.68
    Pa
    -0.66
    inning
    -0.66
     Ending
    -0.66
    oking
    -0.65
    zing
    -0.65
    POSITIVE LOGITS
     nicely
    1.11
     seamlessly
    1.08
     smoothly
    1.07
     itself
    1.03
     automatically
    1.00
     favorably
    0.99
     instantly
    0.97
     easily
    0.95
     beautifully
    0.94
     effortlessly
    0.92
    Activations Density 0.243%

    No Known Activations