© 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. 31271
    Prev
    Next
    INDEX
    Explanations

    technical terms related to network configuration and database connection details

    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
    326
    +0.10
    0.4%
    185
    +0.09
    0.4%
    733
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.08
    584
    +0.09
    0.07
    426
    +0.09
    0.05
    Negative Logits
    ndra
    -0.90
    natureconservancy
    -0.82
    Introduced
    -0.82
    IRD
    -0.78
    andum
    -0.76
    ricks
    -0.76
    sbm
    -0.73
    DragonMagazine
    -0.70
    icion
    -0.68
     Parables
    -0.68
    POSITIVE LOGITS
    localhost
    0.98
    8000
    0.92
     8000
    0.90
     9000
    0.89
    PORT
    0.87
    port
    0.87
    80
    0.85
    3333
    0.84
     port
    0.84
    3000
    0.83
    Activations Density 0.839%

    No Known Activations