© 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. 31481
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to programming and system configuration

    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
    +0.15
    0.7%
    31
    +0.14
    0.6%
    448
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.09
    345
    +0.14
    0.05
    31
    +0.13
    0.05
    Negative Logits
     Canaver
    -0.85
    zag
    -0.80
    spread
    -0.79
    fur
    -0.76
    Hill
    -0.74
    bent
    -0.73
    çĶ°
    -0.71
    ilitarian
    -0.71
    pez
    -0.71
    tall
    -0.70
    POSITIVE LOGITS
     Done
    1.09
     Loading
    1.06
     Finished
    1.06
     Started
    1.05
     installed
    1.04
     Running
    1.01
     initialized
    1.01
     Created
    1.00
     Failed
    0.99
     Configuration
    0.99
    Activations Density 0.504%

    No Known Activations