© 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. 30229
    Prev
    Next
    INDEX
    Explanations

    content related to bloodshed and religious conflicts

    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
    38
    +0.11
    0.5%
    431
    +0.11
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    742
    +0.11
    0.04
    282
    +0.11
    0.07
    750
    +0.10
    0.04
    Negative Logits
    ESA
    -0.91
     pivot
    -0.85
     srfAttach
    -0.82
     piv
    -0.81
     Tacoma
    -0.80
    tel
    -0.80
     Airbus
    -0.77
     Hammond
    -0.76
    flat
    -0.76
     Lear
    -0.76
    POSITIVE LOGITS
     Blood
    2.42
    Blood
    2.28
     blood
    2.20
    blood
    2.06
     Bloody
    1.55
     veins
    1.50
     transf
    1.42
     bleed
    1.37
    blooded
    1.37
     bloodstream
    1.32
    Activations Density 3.179%

    No Known Activations