© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 28485
    Prev
    Next
    INDEX
    Explanations

    relationships between musical techniques and their applications

    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
    762
    +0.10
    0.4%
    439
    +0.10
    0.4%
    458
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.10
    0.21
    540
    +0.10
    0.19
    762
    +0.09
    0.20
    Negative Logits
    asus
    -0.80
    romeda
    -0.77
    rats
    -0.73
    profits
    -0.73
     Shutdown
    -0.72
     Deals
    -0.70
     hemor
    -0.68
     Costco
    -0.68
    BUG
    -0.66
     TEAM
    -0.66
    POSITIVE LOGITS
     suggestive
    1.21
     prominently
    1.11
     motif
    1.10
     depicting
    1.07
     portraying
    1.05
     juxtap
    1.02
     expressive
    1.02
     distinguishing
    1.02
     embell
    1.02
     ("
    1.01
    Activations Density 3.878%

    No Known Activations