© 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. 2-RES-JB
    11. 21487
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "automate" or "automation."

    oai_token-act-pair · gpt-3.5-turbo

    references to automation and automated technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.78
    WHERE
    -0.74
     Wad
    -0.69
    mary
    -0.68
     Hastings
    -0.68
     McKenna
    -0.68
     Michaels
    -0.67
    UGE
    -0.66
     ..........
    -0.64
     Higgins
    -0.63
    POSITIVE LOGITS
    otive
    1.27
    obiles
    1.22
    obile
    1.20
    Autom
    0.97
    odied
    0.91
    aton
    0.87
    merce
    0.87
    atically
    0.86
    obil
    0.86
    otom
    0.85
    Activations Density 0.009%

    No Known Activations