© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 16916
    Prev
    Next
    INDEX
    Explanations

    references to a place or a setting called "Out"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Out" and related terms

    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
    代
    -0.85
    ç·
    -0.78
    terday
    -0.78
    éĥ
    -0.75
    ounter
    -0.69
    ä½ľ
    -0.69
    éĹĺ
    -0.66
    BILITY
    -0.66
    OPLE
    -0.65
    ãĤ¢ãĥ«
    -0.65
    POSITIVE LOGITS
     Runner
    0.83
     Starts
    0.81
    ership
    0.79
     Again
    0.79
     Against
    0.77
     Guard
    0.76
     Ones
    0.75
     Topic
    0.75
     Space
    0.74
     Away
    0.74
    Activations Density 0.089%

    No Known Activations