© 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. 7756
    Prev
    Next
    INDEX
    Explanations

    mentions of official statements or announcements by various entities

    oai_token-act-pair · gpt-3.5-turbo

    formal announcements or statements related to events or legal matters

    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
    ".[
    -0.96
     whilst
    -0.88
    Âł
    -0.83
    âĢ¦
    -0.81
    "—
    -0.80
     [âĢ¦]
    -0.80
    "âĢ¦
    -0.75
    ,—
    -0.75
    !".
    -0.74
    )[
    -0.74
    POSITIVE LOGITS
     spokeswoman
    0.73
     condolences
    0.65
     Hernandez
    0.64
    arnaev
    0.63
     cellphone
    0.63
     NAACP
    0.61
     spokesman
    0.61
     Friday
    0.60
    ___
    0.60
    ernandez
    0.60
    Activations Density 1.298%

    No Known Activations