© 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. 9-RES-JB
    11. 7412
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a significant change or shift in a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate significant changes or impacts over time

    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
    oided
    -0.74
     filib
    -0.67
     Alone
    -0.67
     Recomm
    -0.65
    vati
    -0.64
    itia
    -0.64
    agra
    -0.64
     recommendations
    -0.63
    owship
    -0.62
     Abortion
    -0.62
    POSITIVE LOGITS
     toll
    1.07
     downturn
    0.84
     surreal
    0.81
     Toll
    0.73
    arily
    0.70
     stride
    0.67
     twist
    0.67
     shudder
    0.67
     foothold
    0.67
     dimension
    0.66
    Activations Density 0.134%

    No Known Activations