© 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. 29608
    Prev
    Next
    INDEX
    Explanations

    occurrences of the suffix "en" and its variations in words

    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
    635
    +0.11
    0.5%
    459
    +0.09
    0.4%
    477
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.11
    0.03
    314
    +0.09
    -0.00
    232
    +0.09
    0.03
    Negative Logits
    mith
    -0.78
     hitch
    -0.71
     Knot
    -0.71
    theless
    -0.70
    gaard
    -0.66
    boards
    -0.64
     Chop
    -0.62
    oxide
    -0.61
    luster
    -0.59
    pread
    -0.59
    POSITIVE LOGITS
    seless
    1.29
    itent
    1.27
    etr
    1.03
    arios
    1.01
    uating
    0.96
    estate
    0.93
    ultimate
    0.81
    uation
    0.81
    itors
    0.80
    itor
    0.79
    Activations Density 0.284%

    No Known Activations