© 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 EvalsExportsAPI 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. 28211
    Prev
    Next
    INDEX
    Explanations

    instances of the word "collect" and its variations, indicating a focus on gathering or accumulating items or information

    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
    314
    +0.13
    0.6%
    677
    +0.13
    0.6%
    26
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    677
    +0.13
    0.03
    271
    +0.13
    0.03
    585
    +0.12
    0.03
    Negative Logits
    forth
    -0.71
     wrench
    -0.63
    ordering
    -0.61
     unres
    -0.60
    lease
    -0.60
    xus
    -0.59
    oly
    -0.59
     Nanto
    -0.58
    ffe
    -0.58
    hift
    -0.58
    POSITIVE LOGITS
    ibles
    1.08
     signatures
    1.03
     dust
    1.01
    ivist
    0.97
    ennial
    0.87
    ivism
    0.81
    ible
    0.80
    ively
    0.79
     dues
    0.79
    STON
    0.78
    Activations Density 0.187%

    No Known Activations