© 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. 9229
    Prev
    Next
    INDEX
    Explanations

    words related to family and personal relationships

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to classification and identification

    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
    ocaust
    -0.62
    ibrary
    -0.61
     Framework
    -0.57
    ript
    -0.56
    urgy
    -0.55
    roma
    -0.55
    gage
    -0.54
     Prohibition
    -0.53
    rican
    -0.53
    efficiency
    -0.53
    POSITIVE LOGITS
     alike
    1.11
     versa
    1.10
     accordingly
    0.91
     thereafter
    0.81
     thereto
    0.78
     thereof
    0.77
     respectively
    0.72
     therein
    0.70
    axter
    0.69
     ensued
    0.68
    Activations Density 0.746%

    No Known Activations