© 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. 32374
    Prev
    Next
    INDEX
    Explanations

    topics related to complexity and structural forms in various contexts

    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
    534
    +0.15
    0.7%
    282
    +0.14
    0.6%
    412
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    132
    +0.15
    0.14
    401
    +0.14
    0.22
    282
    +0.11
    0.20
    Negative Logits
    Recomm
    -0.66
     Learns
    -0.61
     Kills
    -0.58
    laughs
    -0.57
    Returns
    -0.55
    ãĥ³ãĤ¸
    -0.55
    igr
    -0.55
    Beg
    -0.54
    ãĤ¸
    -0.53
    tains
    -0.53
    POSITIVE LOGITS
     are
    2.03
     aren
    1.85
     were
    1.71
     have
    1.63
     weren
    1.61
     seem
    1.56
     comprise
    1.55
     remain
    1.54
     appear
    1.51
     constitute
    1.51
    Activations Density 8.410%

    No Known Activations