© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 18481
    Prev
    Next
    INDEX
    Explanations

    professional analysis using phrases like "Among the <category>"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Among" indicating group-related information or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prol
    -0.67
     commute
    -0.65
    ocene
    -0.65
    nery
    -0.62
    dayName
    -0.61
    oulos
    -0.58
     resonate
    -0.57
    "}],"
    -0.57
    avis
    -0.57
    ocracy
    -0.56
    POSITIVE LOGITS
    st
    1.01
    ership
    0.92
    warts
    0.89
    Īè
    0.87
    ī
    0.81
    eteen
    0.81
    stocks
    0.80
    IJ
    0.80
    %%%%
    0.80
    ĪĴ
    0.80
    Activations Density 0.016%

    No Known Activations