© 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. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5741
    Prev
    Next
    INDEX
    Explanations

    terms related to allergies and immune responses

    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
    350
    +0.14
    0.6%
    274
    +0.11
    0.5%
    161
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.04
    350
    +0.11
    0.02
    516
    +0.10
    0.02
    Negative Logits
    estones
    -0.88
    bourg
    -0.83
    amen
    -0.78
    edom
    -0.74
    anova
    -0.73
    ettes
    -0.70
    lining
    -0.70
    swick
    -0.69
    arity
    -0.69
    arnaev
    -0.67
    POSITIVE LOGITS
     sensit
    1.03
     allergic
    1.01
     intoler
    0.89
     dermat
    0.89
     allergies
    0.87
     allergy
    0.85
     flare
    0.79
     reflex
    0.79
    ensitive
    0.78
     itching
    0.76
    Activations Density 0.134%

    No Known Activations