© 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. 4807
    Prev
    Next
    INDEX
    Explanations

    names, possibly related to accusations or personal information

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities characterized by the word "whose."

    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
    enge
    -0.79
    DT
    -0.79
    BO
    -0.78
    eat
    -0.76
    erman
    -0.76
    zb
    -0.76
    cmp
    -0.76
    ����
    -0.75
    UFC
    -0.73
    GBT
    -0.73
    POSITIVE LOGITS
     sole
    1.29
     motto
    1.18
     ancestors
    1.09
     name
    1.09
     whereabouts
    1.08
     names
    1.01
     identities
    1.00
     livelihood
    1.00
     surname
    0.97
     penchant
    0.97
    Activations Density 0.043%

    No Known Activations