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

    Neuronpedia

    Jacobian LensNEW
    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. 16642
    Prev
    Next
    INDEX
    Explanations

    names or specific phrases containing the syllable "av"

    oai_token-act-pair · gpt-3.5-turbo

    references to the player "Pavlich."

    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
    ©¶æ
    -0.77
    utenant
    -0.69
     profiling
    -0.66
    backer
    -0.64
     trademark
    -0.62
     crochet
    -0.61
     regress
    -0.61
    POS
    -0.60
     phenomen
    -0.60
    prints
    -0.60
    POSITIVE LOGITS
    irus
    1.35
    oided
    1.19
    ascular
    1.11
    itational
    1.07
    arro
    1.07
    oice
    1.05
    ille
    1.05
    ision
    1.05
    atars
    1.05
    enture
    1.04
    Activations Density 0.032%

    No Known Activations