© 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. 8-RES-JB
    11. 482
    Prev
    Next
    INDEX
    Explanations

    conditional statements that involve permissions or restrictions

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases that indicate permission or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lez
    -0.93
    ãĤ§
    -0.81
    Dust
    -0.71
     ));
    -0.70
    jab
    -0.69
    ãĥ¼ãĤ¯
    -0.68
    hill
    -0.68
    Poké
    -0.67
    --------------------------------------------------------
    -0.66
     squeeze
    -0.65
    POSITIVE LOGITS
     specified
    1.07
     lawfully
    1.01
     warranted
    0.94
     accompanied
    0.92
     practicable
    0.90
     necessary
    0.89
     expressly
    0.86
     deemed
    0.86
     requested
    0.86
     adjud
    0.85
    Activations Density 0.176%

    No Known Activations