© 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. 10-RES_POST_32K-OAI
    6. 29929
    Prev
    Next
    INDEX
    Explanations

    concepts related to game mechanics and strategies

    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
    24
    +0.13
    0.6%
    309
    +0.13
    0.6%
    592
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    39
    +0.13
    0.07
    309
    +0.13
    0.04
    597
    +0.12
    0.06
    Negative Logits
    yip
    -1.16
    utterstock
    -0.86
    oppable
    -0.76
    ullivan
    -0.75
    vous
    -0.72
    Assad
    -0.71
     glands
    -0.70
     bait
    -0.70
    otine
    -0.69
     Farage
    -0.69
    POSITIVE LOGITS
     Amon
    1.09
     Shards
    1.03
     Magic
    1.01
     MT
    1.00
     Legacy
    0.99
     Vintage
    0.99
     Standard
    0.94
     Duel
    0.93
     Booster
    0.93
     Modern
    0.92
    Activations Density 2.829%

    No Known Activations