© 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. 5631
    Prev
    Next
    INDEX
    Explanations

    expressions of skepticism or doubt regarding claims

    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
    598
    +0.10
    0.5%
    417
    +0.10
    0.5%
    370
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    650
    +0.10
    0.07
    168
    +0.10
    0.06
    372
    +0.10
    0.05
    Negative Logits
    arez
    -0.83
    orse
    -0.74
    bes
    -0.69
    acca
    -0.68
    UD
    -0.66
    ilet
    -0.66
    aeda
    -0.66
    éĹĺ
    -0.65
    tnc
    -0.65
    dayName
    -0.64
    POSITIVE LOGITS
     nonetheless
    1.48
     nevertheless
    1.14
    etheless
    1.14
     alas
    0.87
     beware
    0.83
     persists
    0.82
     retains
    0.82
     lacks
    0.79
     lacked
    0.76
     does
    0.75
    Activations Density 0.733%

    No Known Activations