© 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. 11-RES-JB
    11. 2099
    Prev
    Next
    INDEX
    Explanations

    words related to titles, such as "Titanic," "titular," and "Title Two."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "title" or variations of it in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.77
    Cause
    -0.65
     incomplete
    -0.65
    âĸ¬
    -0.60
    ITNESS
    -0.57
     CC
    -0.55
    FactoryReloaded
    -0.55
     Processing
    -0.55
     quarters
    -0.55
     Wonderland
    -0.54
    POSITIVE LOGITS
    ular
    1.50
    anic
    1.36
    illation
    1.22
    mouse
    1.13
    bits
    1.06
    ewater
    1.00
    anos
    0.98
    ill
    0.96
    ania
    0.93
    ulus
    0.90
    Activations Density 0.055%

    No Known Activations