© 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. 7997
    Prev
    Next
    INDEX
    Explanations

    terms related to a particular type of disease or medical condition related to blood clotting or genetic disorders

    oai_token-act-pair · gpt-3.5-turbo

    terms related to human ancestry and evolution

    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
     pestic
    -0.85
     carrot
    -0.69
     levers
    -0.67
     Moss
    -0.61
     phased
    -0.60
     patronage
    -0.60
     applic
    -0.60
    xtap
    -0.60
     horizont
    -0.60
     fortun
    -0.59
    POSITIVE LOGITS
    ages
    0.86
    stress
    0.79
    andise
    0.79
    amic
    0.77
    enos
    0.70
    sing
    0.69
    opter
    0.68
    adin
    0.67
    xual
    0.66
    antically
    0.65
    Activations Density 0.097%

    No Known Activations