© 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. 8-RES_POST_32K-OAI
    11. 7426
    Prev
    Next
    INDEX
    Explanations

    numerical values and their associated metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    314
    +0.15
    0.7%
    123
    +0.11
    0.5%
    565
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.05
    472
    +0.11
    0.04
    488
    +0.11
    0.05
    Negative Logits
     exha
    -0.82
     plateau
    -0.71
     affirmation
    -0.70
     tradem
    -0.69
     warr
    -0.67
     referen
    -0.66
     reinstated
    -0.65
     vain
    -0.65
     pastry
    -0.65
     newsp
    -0.65
    POSITIVE LOGITS
    00
    1.22
    503
    1.14
    507
    1.13
    79
    1.13
    750
    1.11
    50
    1.11
    80
    1.10
    887
    1.10
    86
    1.09
    97
    1.09
    Activations Density 0.231%

    No Known Activations