© 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. 0-RES-JB
    11. 12891
    Prev
    Next
    INDEX
    Explanations

    references to the word "Jam" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to a specific name or term, particularly "Jam."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fairy
    -0.75
    fecture
    -0.74
     steroids
    -0.73
    paren
    -0.68
     steroid
    -0.67
    xual
    -0.65
    rogens
    -0.65
     Argent
    -0.65
     leisure
    -0.64
     unic
    -0.64
    POSITIVE LOGITS
     Jam
    3.94
    Jam
    3.08
    jam
    1.75
     Jamal
    1.48
     Jama
    1.36
     jam
    1.27
     Jaw
    1.26
     Jem
    1.26
     Jal
    1.25
     Jer
    1.19
    Activations Density 0.002%

    No Known Activations