© 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. 30668
    Prev
    Next
    INDEX
    Explanations

    references to female spokespersons and family relationships

    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
    742
    +0.11
    0.5%
    334
    +0.10
    0.5%
    446
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    121
    +0.11
    0.09
    308
    +0.10
    0.05
    224
    +0.10
    0.07
    Negative Logits
    kefeller
    -0.83
    cius
    -0.81
    brew
    -0.68
     homebrew
    -0.66
     Lovecraft
    -0.66
    umenthal
    -0.65
    driving
    -0.65
     dstg
    -0.64
     cartridge
    -0.63
    cific
    -0.63
    POSITIVE LOGITS
     Olivia
    1.17
     Caroline
    1.14
     Emma
    1.14
     Charlotte
    1.14
     Natasha
    1.14
     Helena
    1.14
     Sof
    1.13
     Samantha
    1.13
     Amelia
    1.13
     Sana
    1.13
    Activations Density 1.877%

    No Known Activations