© 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. 8-RES_POST_32K-OAI
    6. 5810
    Prev
    Next
    INDEX
    Explanations

    occurrences of the pronoun "I" and its related verb forms, indicating a focus on personal experience or perspective

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    713
    +0.10
    0.5%
    296
    +0.10
    0.4%
    472
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.10
    0.08
    354
    +0.10
    0.08
    551
    +0.10
    0.07
    Negative Logits
     Norn
    -0.73
    lation
    -0.68
    aq
    -0.67
    AY
    -0.67
     Nah
    -0.66
    ardless
    -0.65
    ences
    -0.64
    å
    -0.64
    orf
    -0.64
    reality
    -0.64
    POSITIVE LOGITS
     wish
    0.87
     learnt
    0.78
     prized
    0.78
     wanted
    0.76
     coveted
    0.76
     learned
    0.75
     wished
    0.75
     preferred
    0.71
     cherished
    0.69
     desired
    0.68
    Activations Density 0.427%

    No Known Activations