© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5822
    Prev
    Next
    INDEX
    Explanations

    descriptive qualities and attributes related to experiences and settings

    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
    547
    +0.10
    0.5%
    724
    +0.10
    0.5%
    89
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.10
    0.12
    225
    +0.10
    0.10
    575
    +0.10
    0.10
    Negative Logits
    pedia
    -0.67
    kr
    -0.65
    ificant
    -0.63
    arcity
    -0.63
    ruary
    -0.62
     PowerPoint
    -0.61
    oat
    -0.60
    ãĥķãĤ¡
    -0.59
    arus
    -0.57
     turnover
    -0.56
    POSITIVE LOGITS
     perv
    0.79
    tones
    0.78
    tick
    0.72
     predominant
    0.71
     reminiscent
    0.70
     inherent
    0.67
     Christensen
    0.66
     abound
    0.66
    ennes
    0.65
    jah
    0.64
    Activations Density 1.264%

    No Known Activations