© 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. 13585
    Prev
    Next
    INDEX
    Explanations

    phrases related to behind-the-scenes activities or secrets

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to hidden activities or situations

    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
     �
    -0.83
     ãĢĮ
    -0.78
     «
    -0.68
    arnaev
    -0.66
    essage
    -0.62
     :=
    -0.58
     **
    -0.56
    ãĢĮ
    -0.56
     ---------
    -0.56
     §§
    -0.55
    POSITIVE LOGITS
    "
    1.98
    "?
    1.79
    ",
    1.77
    ".
    1.74
    "!
    1.72
    "—
    1.70
    ":
    1.62
    "âĢ¦
    1.62
    ".[
    1.61
    %"
    1.60
    Activations Density 0.821%

    No Known Activations