© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 29538
    Prev
    Next
    INDEX
    Explanations

    phrases related to memory management issues

    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
    +0.11
    0.5%
    378
    +0.10
    0.5%
    660
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    597
    +0.11
    0.03
    553
    +0.10
    0.02
    655
    +0.10
    0.02
    Negative Logits
     Manson
    -0.67
     smashing
    -0.64
     vengeance
    -0.63
    auld
    -0.62
     Cannes
    -0.60
     apartheid
    -0.58
    ttes
    -0.58
     Sherman
    -0.58
     fiercely
    -0.57
     heaven
    -0.57
    POSITIVE LOGITS
    PUT
    1.25
    file
    0.89
    )=(
    0.86
    bound
    0.85
    lined
    0.83
    line
    0.82
    ahead
    0.79
    most
    0.79
    lining
    0.77
    flow
    0.77
    Activations Density 0.279%

    No Known Activations