© 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. 7541
    Prev
    Next
    INDEX
    Explanations

    mentions of newsletters and email subscriptions

    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
    679
    +0.16
    0.7%
    726
    +0.10
    0.4%
    701
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.16
    0.02
    194
    +0.10
    0.02
    373
    +0.10
    -0.00
    Negative Logits
     Robo
    -0.78
    lihood
    -0.70
    owship
    -0.66
    osponsors
    -0.66
     Curse
    -0.65
    FORMATION
    -0.64
     Diabetes
    -0.62
    ODUCT
    -0.62
     Dolphin
    -0.61
     Bruins
    -0.60
    POSITIVE LOGITS
    rador
    0.87
    yr
    0.83
    unin
    0.76
    rss
    0.76
    ois
    0.75
    uish
    0.74
    oun
    0.74
    etts
    0.73
    ett
    0.72
    sell
    0.71
    Activations Density 0.022%

    No Known Activations