© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 4358
    Prev
    Next
    INDEX
    Explanations

    sequences of characters or symbols that may indicate technical terms or mathematical concepts

    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
    496
    +0.13
    0.6%
    373
    +0.13
    0.6%
    497
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.13
    -0.01
    101
    +0.13
    0.10
    64
    +0.11
    -0.06
    Negative Logits
     exting
    -0.84
     eleph
    -0.82
     tremend
    -0.75
     tradem
    -0.66
    lyak
    -0.64
    icter
    -0.62
     earthqu
    -0.62
     ende
    -0.61
    ©¶æ
    -0.61
    StreamerBot
    -0.61
    POSITIVE LOGITS
     };
    0.69
    Í
    0.69
    };
    0.68
    BILITIES
    0.67
     href
    0.64
    inventoryQuantity
    0.63
    Rap
    0.63
    quickShipAvailable
    0.59
    ;}
    0.58
    _>
    0.58
    Activations Density 0.884%

    No Known Activations