© 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. 4-RES-JB
    11. 564
    Prev
    Next
    INDEX
    Explanations

    the adverb "occasionally"

    oai_token-act-pair · gpt-3.5-turbo

    the word "occasionally" and its variations in different contexts

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

    No Comments

    Negative Logits
    iants
    -0.81
    ye
    -0.74
    Absolutely
    -0.73
    EO
    -0.71
    jing
    -0.71
    sein
    -0.69
    uid
    -0.68
     Warriors
    -0.67
    zyme
    -0.66
    WAR
    -0.66
    POSITIVE LOGITS
     glimps
    1.12
    theless
    1.08
    etheless
    0.99
     reapp
    0.83
     interrupt
    0.81
     encount
    0.81
     bouts
    0.80
     interrupted
    0.79
     exceptions
    0.79
    asionally
    0.78
    Activations Density 0.008%

    No Known Activations