© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-JB
    11. 13204
    Prev
    Next
    INDEX
    Explanations

    names of individuals or places, specifically related to the name "Ogilvy" and "Hamburg 5."

    oai_token-act-pair · gpt-3.5-turbo

    names of awards, locations, and consumables mentioned in the context of events or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĨĴ
    -0.99
     constitu
    -0.69
     Gravity
    -0.69
    eering
    -0.68
    Æ
    -0.68
     thinker
    -0.66
     fundamentalist
    -0.65
    chy
    -0.64
     flock
    -0.64
     pse
    -0.64
    POSITIVE LOGITS
    acious
    1.06
    shaw
    0.84
    lished
    0.81
    Accessory
    0.80
    pole
    0.78
    abilities
    0.78
    mg
    0.78
     Hastings
    0.78
     Sack
    0.77
    grad
    0.77
    Activations Density 0.022%

    No Known Activations