© 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. 29909
    Prev
    Next
    INDEX
    Explanations

    phrases expressing hope, possibility, and potential consequences of actions or inactions

    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
    418
    +0.12
    0.5%
    546
    +0.11
    0.5%
    586
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.12
    0.13
    718
    +0.11
    0.13
    49
    +0.10
    0.12
    Negative Logits
    ãĤ¨ãĥ«
    -0.77
    rawdownloadcloneembedreportprint
    -0.72
    */(
    -0.68
    udge
    -0.64
     Sands
    -0.63
    tyard
    -0.63
     tho
    -0.61
     Palest
    -0.59
    ãĥīãĥ©ãĤ´ãĥ³
    -0.59
     acron
    -0.58
    POSITIVE LOGITS
     unstoppable
    0.78
     doomed
    0.76
     automatically
    0.76
     conclude
    0.75
     worthless
    0.73
     surely
    0.71
     awfully
    0.69
     worthwhile
    0.67
     moot
    0.67
    ))))
    0.66
    Activations Density 4.030%

    No Known Activations