© 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. 10-RES-JB
    11. 18831
    Prev
    Next
    INDEX
    Explanations

    numeric patterns being described or referenced, particularly those involving the terms "long" and "running."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating long-term situations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Compass
    -0.82
     Scrib
    -0.74
     GOODMAN
    -0.72
     Brooke
    -0.71
     Pok
    -0.71
     Polo
    -0.66
     Territories
    -0.66
     Clubs
    -0.65
     Creator
    -0.64
     Robertson
    -0.63
    POSITIVE LOGITS
    term
    1.61
    lasting
    1.46
    awaited
    1.44
    distance
    1.39
    lived
    1.38
    range
    1.37
    standing
    1.36
    established
    1.32
    haired
    1.27
    serving
    1.26
    Activations Density 0.026%

    No Known Activations