© 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. 8-RES-JB
    11. 11494
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical weight

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "heavy" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icho
    -0.88
    DragonMagazine
    -0.80
    urated
    -0.79
    Ĥİ
    -0.74
     Unlimited
    -0.72
    ifice
    -0.72
    isphere
    -0.72
    otiation
    -0.72
    çīĪ
    -0.71
     Kirin
    -0.71
    POSITIVE LOGITS
    weights
    1.75
    weight
    1.31
     hitters
    1.26
     hitter
    1.20
     lifting
    1.15
     weights
    1.04
     duty
    1.04
    metal
    0.97
     weight
    0.96
     burdens
    0.95
    Activations Density 0.036%

    No Known Activations