© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8811
    Prev
    Next
    INDEX
    Explanations

    mentions of team or collective entities, particularly in a sports context

    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%
    415
    +0.12
    0.5%
    152
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.15
    0.07
    373
    +0.12
    -0.05
    284
    +0.11
    0.05
    Negative Logits
    phrine
    -0.87
    ozy
    -0.75
    alam
    -0.72
    yip
    -0.70
    hens
    -0.68
    hower
    -0.67
    onal
    -0.67
    bush
    -0.60
    iasm
    -0.59
    nings
    -0.59
    POSITIVE LOGITS
    aiden
    0.65
    ¶æ
    0.64
    Ń·
    0.63
    Container
    0.62
    ittal
    0.61
    iage
    0.60
    prototype
    0.59
    ardless
    0.59
    UME
    0.58
    operated
    0.56
    Activations Density 0.951%

    No Known Activations