© 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. 31130
    Prev
    Next
    INDEX
    Explanations

    terms related to game mechanics and abilities

    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
    676
    +0.14
    0.6%
    419
    +0.13
    0.6%
    56
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.14
    0.09
    314
    +0.13
    0.00
    588
    +0.12
    0.06
    Negative Logits
    çĶ°
    -0.92
     bicy
    -0.78
     advertising
    -0.74
     AMA
    -0.72
     discontin
    -0.71
     IMAGES
    -0.71
     Tsarnaev
    -0.69
     advoc
    -0.69
     paralle
    -0.69
    soDeliveryDate
    -0.68
    POSITIVE LOGITS
    romancer
    1.27
    Spell
    1.18
    Armor
    1.05
    Weapon
    1.04
     Weapon
    1.04
     Spell
    1.01
    erity
    0.99
    Knight
    0.98
    Spawn
    0.96
    erker
    0.96
    Activations Density 0.571%

    No Known Activations