© 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. 29981
    Prev
    Next
    INDEX
    Explanations

    presence of the word "est" and variations of "vag" related terms

    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
    685
    +0.11
    0.5%
    692
    +0.10
    0.5%
    19
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.11
    -0.00
    288
    +0.10
    0.03
    738
    +0.10
    0.01
    Negative Logits
    llor
    -0.64
    Requirements
    -0.60
    lly
    -0.60
    tex
    -0.60
    ETF
    -0.58
    asley
    -0.58
    vier
    -0.58
     Accountability
    -0.57
    theless
    -0.57
    Disk
    -0.57
    POSITIVE LOGITS
    hetic
    1.08
    rang
    1.01
    rus
    0.93
    ranging
    0.93
    rone
    0.89
    rants
    0.88
    rue
    0.88
    hetical
    0.87
    uary
    0.87
    raint
    0.87
    Activations Density 0.152%

    No Known Activations