© 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. 12087
    Prev
    Next
    INDEX
    Explanations

    specific entity names or terms, potentially related to investigative or legal contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to people, particularly in the context of relationships or events involving them

    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
    yz
    -0.71
    PN
    -0.66
    Compare
    -0.65
    GMT
    -0.63
    SIGN
    -0.63
     Pwr
    -0.61
     Presidents
    -0.61
    Anonymous
    -0.60
    GBT
    -0.60
    TRUMP
    -0.59
    POSITIVE LOGITS
     grandson
    0.86
    wered
    0.85
     own
    0.85
    alty
    0.82
    ullivan
    0.82
    terday
    0.80
     granddaughter
    0.79
    anton
    0.77
     son
    0.77
     footsteps
    0.77
    Activations Density 0.143%

    No Known Activations