© 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. 11-RES-JB
    11. 20442
    Prev
    Next
    INDEX
    Explanations

    words related to protest, rejection, or opposition

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "reb" indicating a form of recovery or revival

    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
     Kafka
    -0.67
     flu
    -0.60
    âĢ¢âĢ¢
    -0.60
     LIA
    -0.59
    lihood
    -0.59
     Slov
    -0.59
     Kern
    -0.59
     Abram
    -0.58
     stewards
    -0.58
    falls
    -0.57
    POSITIVE LOGITS
    uked
    1.50
    uffed
    1.47
    ounding
    1.44
    ounded
    1.42
    ukes
    1.37
    oots
    1.27
    uff
    1.27
    ooting
    1.25
    uilding
    1.21
    road
    1.20
    Activations Density 0.032%

    No Known Activations