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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 4738
    Prev
    Next
    INDEX
    Explanations

    medical terminologies related to injuries and surgeries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    373
    +0.12
    0.5%
    702
    +0.11
    0.5%
    629
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    516
    +0.12
    0.05
    260
    +0.11
    0.07
    319
    +0.10
    0.06
    Negative Logits
    abiding
    -0.76
    soDeliveryDate
    -0.74
    eworld
    -0.72
    iquette
    -0.71
     queues
    -0.71
    packs
    -0.70
     fleets
    -0.70
     sqor
    -0.69
    istas
    -0.68
    idity
    -0.68
    POSITIVE LOGITS
     amput
    0.92
     surgery
    0.87
     lig
    0.85
     Surgery
    0.81
    rafted
    0.81
     tendon
    0.80
     suffered
    0.78
     Ambro
    0.73
     Rehab
    0.73
    Doctors
    0.72
    Activations Density 1.707%

    No Known Activations