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

    Neuronpedia

    Jacobian LensNEW
    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. 5039
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate significant accomplishments or noteworthy attributes

    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
    474
    +0.11
    0.5%
    463
    +0.11
    0.5%
    331
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.11
    0.19
    362
    +0.11
    0.10
    159
    +0.10
    0.08
    Negative Logits
    matter
    -0.85
     processes
    -0.75
    gru
    -0.75
    inventoryQuantity
    -0.74
     process
    -0.73
    ileaks
    -0.72
    ffect
    -0.69
    terday
    -0.67
     matter
    -0.65
     Matter
    -0.64
    POSITIVE LOGITS
     berth
    1.00
     Pulitzer
    0.95
     lucrative
    0.88
     residency
    0.85
     stint
    0.84
     reputation
    0.84
     fortune
    0.83
     foothold
    0.82
     fortunes
    0.80
     hefty
    0.77
    Activations Density 0.775%

    No Known Activations