© 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. 4-RES-JB
    11. 15530
    Prev
    Next
    INDEX
    Explanations

    medical conditions or terms related to the central nervous system

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical conditions affecting the central nervous system

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

    No Comments

    Negative Logits
    Ore
    -0.74
    KY
    -0.73
     Eleven
    -0.71
    ãĥ´ãĤ¡
    -0.71
     Breaker
    -0.67
    emo
    -0.66
    QL
    -0.66
    MON
    -0.65
    fried
    -0.64
     Beacon
    -0.64
    POSITIVE LOGITS
     diffusion
    0.80
    ioxide
    0.79
     overdose
    0.74
    utic
    0.71
    ople
    0.67
     diffuse
    0.66
     aeros
    0.66
     aim
    0.66
    rogen
    0.65
     melan
    0.65
    Activations Density 0.000%

    No Known Activations