© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 31839
    Prev
    Next
    INDEX
    Explanations

    instructions and commands related to installation and setup processes

    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
    296
    +0.10
    0.5%
    517
    +0.10
    0.5%
    29
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.11
    267
    +0.10
    0.08
    496
    +0.09
    0.10
    Negative Logits
     lasted
    -0.70
     preserved
    -0.68
     retained
    -0.63
     mourning
    -0.61
     exempted
    -0.60
     acquitted
    -0.60
     disappro
    -0.59
     delayed
    -0.58
     outl
    -0.58
     valued
    -0.58
    POSITIVE LOGITS
    Simply
    1.08
     simply
    0.99
     Simply
    0.98
    Press
    0.88
    Tap
    0.86
     CLICK
    0.85
    click
    0.83
    Click
    0.81
     swipe
    0.81
    Open
    0.80
    Activations Density 1.502%

    No Known Activations