© 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. 8-RES-JB
    11. 6330
    Prev
    Next
    INDEX
    Explanations

    phrases containing the contraction "they'd"

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'd' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sleeping
    -0.66
     Scholar
    -0.63
     Tayyip
    -0.61
     Drum
    -0.60
     Koen
    -0.59
     punitive
    -0.58
     Spur
    -0.58
     Penguin
    -0.57
     Continental
    -0.57
     Shogun
    -0.57
    POSITIVE LOGITS
    ividual
    1.45
    rew
    1.19
    iversity
    1.19
    iscover
    1.08
    onna
    1.04
    ynamic
    1.04
    ynam
    1.03
    ivers
    1.03
    ude
    1.03
    iamond
    1.03
    Activations Density 0.023%

    No Known Activations