© 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 EvalsExportsinterp-engineNEWAPI 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. 9674
    Prev
    Next
    INDEX
    Explanations

    words associated with government, politics, and national security

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "is" and its variations in different contexts

    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
     Telesc
    -0.84
    ossom
    -0.69
     Stones
    -0.68
    ousy
    -0.64
    izable
    -0.64
     occurs
    -0.63
     lasts
    -0.62
    rouse
    -0.61
    owan
    -0.59
    rous
    -0.59
    POSITIVE LOGITS
     obligated
    1.04
     advised
    1.04
     pleased
    1.03
     willing
    1.03
     aware
    1.02
     obliged
    1.00
     tasked
    1.00
     eager
    1.00
     gearing
    0.98
    senal
    0.98
    Activations Density 0.446%

    No Known Activations