© 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. 9476
    Prev
    Next
    INDEX
    Explanations

    actions that involve physical or emotional interaction with others

    oai_token-act-pair · gpt-3.5-turbo

    actions related to emotional expressions and decision-making

    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
    umn
    -0.64
    roma
    -0.62
    MSN
    -0.60
    uum
    -0.60
     Extrem
    -0.60
    utenberg
    -0.59
     ][
    -0.59
    >>\
    -0.58
    olon
    -0.57
    UGC
    -0.57
    POSITIVE LOGITS
     accordingly
    0.99
     alike
    0.88
     oneself
    0.84
     yourself
    0.83
     ourselves
    0.81
     yourselves
    0.79
     versa
    0.78
     them
    0.76
    ings
    0.74
    ables
    0.73
    Activations Density 0.393%

    No Known Activations