© 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. 0-RES-JB
    11. 18891
    Prev
    Next
    INDEX
    Explanations

    words related to orthopedics

    oai_token-act-pair · gpt-3.5-turbo

    words related to medical or surgical operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     harbour
    -0.68
     prompts
    -0.64
     Sauce
    -0.63
     disg
    -0.62
    prom
    -0.62
    adh
    -0.61
    Simon
    -0.60
    claw
    -0.59
     rumours
    -0.59
     favourable
    -0.59
    POSITIVE LOGITS
    oped
    3.26
     bothered
    1.03
    tted
    0.94
    uds
    0.91
    tarian
    0.85
    IFIED
    0.84
    ifle
    0.84
     Raider
    0.83
    oled
    0.82
     chees
    0.79
    Activations Density 0.025%

    No Known Activations