© 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. 19402
    Prev
    Next
    INDEX
    Explanations

    the word "quintessential" with varying degrees of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to quantiles, particularly "quintiles" and "quartiles."

    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
     palms
    -0.59
     speech
    -0.59
     tissue
    -0.58
     Lyme
    -0.58
     mamm
    -0.58
    cock
    -0.57
     tissues
    -0.56
     conditioning
    -0.55
     goodbye
    -0.55
     introdu
    -0.55
    POSITIVE LOGITS
    essential
    1.38
    uple
    1.29
    naire
    1.03
    ieth
    0.96
    ophon
    0.95
    ilian
    0.95
    eenth
    0.94
    illion
    0.94
    iles
    0.94
    oise
    0.93
    Activations Density 0.034%

    No Known Activations