© 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. 6492
    Prev
    Next
    INDEX
    Explanations

    references to brand names and their associations

    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
    467
    +0.11
    0.5%
    9
    +0.11
    0.5%
    39
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    129
    +0.11
    0.02
    284
    +0.11
    0.02
    711
    +0.11
    0.01
    Negative Logits
    atche
    -0.72
    leep
    -0.72
     passage
    -0.66
     traject
    -0.65
     remed
    -0.65
    berra
    -0.65
    veyard
    -0.65
     interrog
    -0.64
     births
    -0.64
    poral
    -0.64
    POSITIVE LOGITS
     Gleaming
    0.89
    lished
    0.85
    ishable
    0.83
    ished
    0.82
    isher
    0.81
    ciating
    0.80
    Cola
    0.79
    uously
    0.74
    ishing
    0.73
    ellation
    0.71
    Activations Density 0.496%

    No Known Activations