© 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. 10-RES-JB
    11. 16660
    Prev
    Next
    INDEX
    Explanations

    words related to organizations or institutions, especially ones with the word "Center" in their names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various organizations or institutions, particularly those associated with the word "Center."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     experien
    -0.62
    ths
    -0.62
     intuition
    -0.62
    unctions
    -0.61
    soDeliveryDate
    -0.60
     yog
    -0.59
     Luthor
    -0.59
     perfection
    -0.59
     retard
    -0.58
    added
    -0.58
    POSITIVE LOGITS
    pieces
    0.99
    piece
    0.89
    point
    0.84
    fold
    0.82
    eous
    0.81
    tyard
    0.81
    arity
    0.81
     Against
    0.81
    Point
    0.79
    clair
    0.75
    Activations Density 0.026%

    No Known Activations