© 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. 32524
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the importance of maintaining control or secrecy

    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
    355
    +0.10
    0.5%
    204
    +0.10
    0.5%
    282
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    531
    +0.10
    0.03
    282
    +0.10
    0.03
    526
    +0.10
    -0.00
    Negative Logits
    eware
    -0.67
    rehens
    -0.66
    iller
    -0.64
     reserves
    -0.62
    mson
    -0.62
    arest
    -0.59
    eworks
    -0.59
    llah
    -0.59
    olars
    -0.58
    WARE
    -0.58
    POSITIVE LOGITS
     classy
    0.69
     simple
    0.69
    UG
    0.67
     Simple
    0.66
     together
    0.65
     conflic
    0.62
    rio
    0.61
    simple
    0.61
     bottled
    0.60
    alo
    0.59
    Activations Density 0.326%

    No Known Activations