© 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. 3-RES-JB
    11. 18553
    Prev
    Next
    INDEX
    Explanations

    the word "Fat" with varying degrees of activation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Fat," likely in reference to a specific group or individual related to political or social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.90
    sers
    -0.79
    ä
    -0.70
     Vaugh
    -0.69
     patented
    -0.65
    ILLE
    -0.65
     WARN
    -0.64
     AZ
    -0.64
    wordpress
    -0.64
    election
    -0.63
    POSITIVE LOGITS
    igue
    1.30
    Fat
    0.99
    fat
    0.97
    cule
    0.88
    adin
    0.87
    ty
    0.86
    liction
    0.86
    emen
    0.86
    rition
    0.84
    ishes
    0.83
    Activations Density 0.006%

    No Known Activations