© 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. 1-RES-JB
    11. 12259
    Prev
    Next
    INDEX
    Explanations

    commands or instructions to delete specific content or files

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "delete" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    annis
    -0.91
    asio
    -0.76
    llah
    -0.73
    senal
    -0.73
     negotiators
    -0.70
    uay
    -0.69
    orthy
    -0.69
    ¶æ
    -0.67
     Huck
    -0.67
    acle
    -0.67
    POSITIVE LOGITS
     delete
    1.01
     Delete
    0.98
     delet
    0.91
    Delete
    0.89
    delete
    0.88
     deleting
    0.82
     deletion
    0.81
     deleted
    0.74
    ãĤ´
    0.67
    hammer
    0.65
    Activations Density 0.012%

    No Known Activations