© 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. 7395
    Prev
    Next
    INDEX
    Explanations

    instances where deletion or removing something is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "delete" and related phrases indicating removal or deletion of accounts and content

    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
    annis
    -0.81
    ebus
    -0.80
    orsi
    -0.73
    heit
    -0.72
     negotiators
    -0.71
    asio
    -0.68
    Building
    -0.67
    verning
    -0.66
    croft
    -0.65
    acs
    -0.65
    POSITIVE LOGITS
     deleted
    0.89
     delet
    0.88
     delete
    0.83
     Delete
    0.83
     unnecessary
    0.72
     deleting
    0.69
    delete
    0.68
     scrolls
    0.68
    username
    0.67
    aneous
    0.65
    Activations Density 0.062%

    No Known Activations