© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES_POST_32K-OAI
    6. 4579
    Prev
    Next
    INDEX
    Explanations

    specific graphics processing unit (GPU) brands and models

    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
    373
    +0.15
    0.7%
    57
    +0.13
    0.6%
    48
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    538
    +0.15
    0.01
    288
    +0.13
    0.01
    326
    +0.11
    0.01
    Negative Logits
     orally
    -0.80
    alty
    -0.77
    nets
    -0.76
    Interstitial
    -0.76
    eering
    -0.71
     Debor
    -0.71
    chy
    -0.71
    atively
    -0.69
    shake
    -0.67
    pit
    -0.65
    POSITIVE LOGITS
     980
    0.88
     680
    0.79
     1080
    0.79
     TIT
    0.78
     970
    0.78
     1050
    0.76
    owship
    0.75
    680
    0.74
     960
    0.73
     1070
    0.72
    Activations Density 0.018%

    No Known Activations