© 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. 10-RES_POST_32K-OAI
    11. 28202
    Prev
    Next
    INDEX
    Explanations

    topics related to public media and online content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    +0.13
    0.6%
    314
    +0.13
    0.6%
    565
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.13
    -0.01
    373
    +0.13
    -0.03
    232
    +0.11
    0.03
    Negative Logits
    nces
    -0.92
    yip
    -0.78
    netflix
    -0.69
    cellence
    -0.66
    itiveness
    -0.65
    yssey
    -0.63
     awa
    -0.63
    nery
    -0.60
    nings
    -0.59
    achus
    -0.57
    POSITIVE LOGITS
    Ph
    0.72
    Unknown
    0.70
    Emer
    0.65
    Av
    0.62
    éŃĶ
    0.60
    ãĥł
    0.60
    Weapon
    0.59
    ãĥij
    0.59
    reath
    0.59
    é£
    0.58
    Activations Density 0.215%

    No Known Activations