© 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. 2837
    Prev
    Next
    INDEX
    Explanations

    phrases related to time durations

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

    comparisons involving quantities or amounts

    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
    swick
    -0.74
    aci
    -0.71
    çīĪ
    -0.71
    aez
    -0.71
    ãĤ´ãĥ³
    -0.71
    ¶ħ
    -0.71
    olate
    -0.71
    isson
    -0.69
    omas
    -0.69
    OE
    -0.67
    POSITIVE LOGITS
     stellar
    1.04
     optimal
    0.93
     flattering
    0.91
     ideal
    0.90
     half
    0.90
     desirable
    0.83
     satisfactory
    0.83
     optimum
    0.80
     ½
    0.79
     halfway
    0.76
    Activations Density 0.046%

    No Known Activations