© 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. 7292
    Prev
    Next
    INDEX
    Explanations

    phrases contrasting different perspectives or approaches

    oai_token-act-pair · gpt-3.5-turbo

    phrases or constructs that indicate negation or the idea of "not."

    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
    eur
    -0.74
    kamp
    -0.72
    stakes
    -0.69
    ction
    -0.68
    velt
    -0.64
    oise
    -0.63
    itor
    -0.63
    hower
    -0.62
    WER
    -0.62
    itiz
    -0.61
    POSITIVE LOGITS
     necessarily
    1.39
    icably
    1.33
    epad
    1.14
    icable
    1.06
    withstanding
    0.97
    orious
    0.96
     bothering
    0.91
    etheless
    0.90
    eworthy
    0.85
     exactly
    0.84
    Activations Density 0.144%

    No Known Activations