© 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. 16237
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "occasionally."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "occasionally"

    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
    iants
    -0.78
    ye
    -0.76
    shi
    -0.75
    sein
    -0.71
    bern
    -0.71
     Warriors
    -0.70
    EO
    -0.69
    rets
    -0.69
    jing
    -0.69
     Reasons
    -0.68
    POSITIVE LOGITS
    theless
    1.11
     glimps
    1.05
    etheless
    1.00
     occas
    0.92
     reapp
    0.87
     encount
    0.86
    interstitial
    0.83
     interrupted
    0.82
     compr
    0.82
     interrupt
    0.81
    Activations Density 0.009%

    No Known Activations