© 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. 6-RES-JB
    11. 13754
    Prev
    Next
    INDEX
    Explanations

    phrases related to distinct or unique sets of items or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to different sets of criteria or guidelines

    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
    issance
    -0.77
    Fight
    -0.74
    ï¸ı
    -0.70
    BLE
    -0.69
    loo
    -0.67
     Souls
    -0.66
    perse
    -0.65
    ãĥĨãĤ£
    -0.65
    IBLE
    -0.64
     Taste
    -0.63
    POSITIVE LOGITS
    offs
    1.12
    tle
    0.99
    list
    0.87
    ter
    0.84
    eq
    0.83
    ters
    0.81
    off
    0.81
    meal
    0.80
    limits
    0.79
    tering
    0.78
    Activations Density 0.031%

    No Known Activations