© 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. 22260
    Prev
    Next
    INDEX
    Explanations

    sentence-ending phrases used in conversations

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation

    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
     starved
    -0.72
    ersive
    -0.68
    aband
    -0.68
     purse
    -0.68
    untarily
    -0.67
     pill
    -0.67
    aganda
    -0.67
    ¶ħ
    -0.66
    unker
    -0.65
    itionally
    -0.65
    POSITIVE LOGITS
     Adds
    0.95
     Asked
    0.95
     Ultimately
    0.91
     Nevertheless
    0.86
     Those
    0.86
     Such
    0.85
     Refer
    0.85
     Eventually
    0.84
     Then
    0.84
     Saying
    0.83
    Activations Density 0.096%

    No Known Activations