© 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. 5837
    Prev
    Next
    INDEX
    Explanations

    expressions related to mathematical equations or equalities

    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
    213
    +0.12
    0.5%
    496
    +0.11
    0.5%
    276
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    57
    +0.12
    0.02
    289
    +0.11
    0.01
    326
    +0.10
    0.02
    Negative Logits
    istics
    -0.75
    natureconservancy
    -0.72
    icious
    -0.71
     Torrent
    -0.68
    istically
    -0.67
    istic
    -0.65
    izations
    -0.64
    adium
    -0.63
     CHR
    -0.62
     caps
    -0.61
    POSITIVE LOGITS
    yip
    0.86
    terday
    0.84
    eus
    0.79
    eny
    0.78
    bow
    0.78
    iron
    0.78
    bows
    0.76
    imeter
    0.75
    elf
    0.74
    err
    0.74
    Activations Density 0.099%

    No Known Activations