© 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. 7-RES-JB
    11. 12446
    Prev
    Next
    INDEX
    Explanations

    word starting with an apostrophe

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the apostrophe character used in contractions or possessives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Archdemon
    -0.85
     ..............
    -0.67
     Hendricks
    -0.66
     Vaugh
    -0.65
     Ames
    -0.64
     printer
    -0.63
     Izan
    -0.63
     polyg
    -0.63
     Leilan
    -0.62
     Argon
    -0.61
    POSITIVE LOGITS
    cause
    1.44
    til
    1.36
    Interstitial
    1.31
    Mech
    1.20
    tis
    1.20
    taboola
    1.11
    Cause
    1.04
    keeper
    0.97
    -'
    0.97
    round
    0.96
    Activations Density 0.050%

    No Known Activations