© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7-RES-JB
    11. 4359
    Prev
    Next
    INDEX
    Explanations

    phrases related to ladder safety and ladder-related instructions

    oai_token-act-pair · gpt-3.5-turbo

    warnings or instructions regarding safety and caution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]."
    -0.90
    ).[
    -0.84
    '."
    -0.83
    .'"
    -0.82
    .).
    -0.77
    ."[
    -0.77
    anwhile
    -0.67
    ".[
    -0.67
    )."
    -0.64
    .")
    -0.60
    POSITIVE LOGITS
     ||
    0.75
     ?
    0.71
    ?",
    0.65
     ·
    0.62
     nor
    0.60
     or
    0.60
     /
    0.58
     OR
    0.58
     \'
    0.57
     &&
    0.56
    Activations Density 1.990%

    No Known Activations