© 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. 12-RES-JB
    11. 2909
    Prev
    Next
    INDEX
    Explanations

    phrases related to video game characters and strategies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases that pose questions or inquire about the best options or alternatives in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    hops
    -0.76
    runs
    -0.74
    adoes
    -0.72
    sheets
    -0.71
    alone
    -0.69
    hips
    -0.69
    alions
    -0.68
    mares
    -0.68
    irms
    -0.67
    alus
    -0.67
    POSITIVE LOGITS
     fuss
    1.13
     difference
    1.10
     significance
    1.09
     Difference
    0.98
     purpose
    0.97
     optimum
    0.95
     reperc
    0.90
     heck
    0.90
     motive
    0.90
     implications
    0.89
    Activations Density 0.154%

    No Known Activations