© 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 EvalsExportsinterp-engineNEWAPI 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. 28100
    Prev
    Next
    INDEX
    Explanations

    references to awareness, observation, and recognition of experiences or events

    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
    192
    +0.11
    0.5%
    331
    +0.10
    0.4%
    218
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.11
    0.18
    184
    +0.10
    0.08
    408
    +0.10
    0.16
    Negative Logits
    accompanied
    -0.65
    ortment
    -0.65
    utenberg
    -0.62
    onomy
    -0.61
    loo
    -0.57
    cius
    -0.57
     srfAttach
    -0.56
     slowly
    -0.56
    mostly
    -0.56
    oÄŁ
    -0.55
    POSITIVE LOGITS
     anything
    2.07
     any
    1.99
     nor
    1.86
     anybody
    1.81
     anymore
    1.80
     anyone
    1.75
     ANY
    1.69
    anything
    1.58
     anywhere
    1.50
     slightest
    1.45
    Activations Density 3.189%

    No Known Activations