© 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. 5639
    Prev
    Next
    INDEX
    Explanations

    phrases indicating time-sensitive or urgent events

    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
    20
    +0.10
    0.5%
    373
    +0.10
    0.5%
    444
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.10
    -0.02
    284
    +0.10
    0.03
    136
    +0.10
    0.03
    Negative Logits
    cius
    -0.92
    INO
    -0.83
    nai
    -0.79
     intrins
    -0.76
    gio
    -0.69
    veland
    -0.68
    heit
    -0.68
    itud
    -0.67
     actionGroup
    -0.67
    orney
    -0.65
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    0.67
    usercontent
    0.66
    utory
    0.66
     Haku
    0.62
     Monkey
    0.60
    birth
    0.60
    Title
    0.60
     Rumble
    0.58
     Whats
    0.56
    mouse
    0.55
    Activations Density 0.249%

    No Known Activations