© 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 EvalsExportsAPI 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. 13567
    Prev
    Next
    INDEX
    Explanations

    words related to the fast-food industry

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to fast food and its industry

    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
     Bild
    -0.66
     masks
    -0.66
    çīĪ
    -0.65
    ynski
    -0.64
     merits
    -0.64
     Glass
    -0.63
     Benefit
    -0.62
     ceiling
    -0.61
     Loren
    -0.60
     Pengu
    -0.60
    POSITIVE LOGITS
    paced
    1.49
    growing
    1.36
    moving
    1.32
    track
    1.24
    acting
    1.22
    twitch
    1.16
    rising
    1.16
    changing
    1.14
    talking
    1.13
    enough
    1.13
    Activations Density 0.020%

    No Known Activations