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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 16099
    Prev
    Next
    INDEX
    Explanations

    phrases related to deletion or removal actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "delete" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Serv
    -0.71
     Semin
    -0.68
     Providence
    -0.66
     pitched
    -0.66
     Olymp
    -0.65
     Baker
    -0.64
     Rising
    -0.63
     Compet
    -0.63
     Watts
    -0.63
     benef
    -0.63
    POSITIVE LOGITS
     delete
    3.43
    delete
    2.55
     deleting
    2.46
     delet
    2.32
    Delete
    2.24
     deletion
    2.23
     Delete
    2.17
     erase
    1.75
     overwrite
    1.63
     uninstall
    1.61
    Activations Density 0.020%

    No Known Activations