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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16194
    Prev
    Next
    INDEX
    Explanations

    terms related to automation or automated processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to automation and automakers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.79
     Wad
    -0.74
     Hastings
    -0.74
    UGE
    -0.73
    WHERE
    -0.72
     Michaels
    -0.71
     McKenna
    -0.69
    mary
    -0.68
    patrick
    -0.67
     Birch
    -0.66
    POSITIVE LOGITS
    otive
    1.30
    obiles
    1.28
    obile
    1.25
    aton
    1.00
    ated
    0.99
    Autom
    0.98
    atically
    0.94
    otor
    0.91
    odied
    0.89
    agically
    0.86
    Activations Density 0.010%

    No Known Activations