© 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. 29917
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with interpersonal dynamics and social interactions

    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
    373
    +0.17
    0.8%
    656
    +0.11
    0.5%
    60
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    143
    +0.17
    0.01
    640
    +0.11
    0.02
    218
    +0.10
    0.01
    Negative Logits
    CVE
    -0.80
    âĶĢâĶĢâĶĢâĶĢ
    -0.80
     UW
    -0.78
    Reviewer
    -0.76
    \\\\\\\\
    -0.75
    WA
    -0.74
    *:
    -0.73
    yll
    -0.71
    ITNESS
    -0.70
    ï¸
    -0.69
    POSITIVE LOGITS
    ossal
    0.76
     Fiat
    0.71
     Javier
    0.70
    Base
    0.64
     Benz
    0.64
    billion
    0.62
    Benz
    0.61
    iegel
    0.61
     droid
    0.61
    Italian
    0.60
    Activations Density 0.031%

    No Known Activations