© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5515
    Prev
    Next
    INDEX
    Explanations

    names that are variations or derivatives of "Rod" or "Rodriguez."

    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
    223
    +0.10
    0.5%
    554
    +0.09
    0.4%
    35
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    628
    +0.10
    0.02
    316
    +0.09
    0.01
    35
    +0.09
    0.01
    Negative Logits
    creen
    -0.77
    places
    -0.63
    phis
    -0.60
     Bears
    -0.59
    izations
    -0.57
     spect
    -0.56
     Pixie
    -0.56
     resistor
    -0.55
     Tsukuyomi
    -0.55
    opsy
    -0.55
    POSITIVE LOGITS
    gers
    1.06
    rig
    0.99
    olf
    0.96
    erick
    0.95
    acity
    0.94
    ynamic
    0.93
    olph
    0.92
    erer
    0.89
    cliffe
    0.87
    ynam
    0.83
    Activations Density 0.070%

    No Known Activations