© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6250
    Prev
    Next
    INDEX
    Explanations

    the word "one" or variations of it indicating singularity or uniqueness

    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
    55
    +0.11
    0.5%
    393
    +0.10
    0.4%
    205
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    377
    +0.11
    0.03
    553
    +0.10
    0.02
    542
    +0.09
    0.03
    Negative Logits
    tnc
    -0.74
    edIn
    -0.65
    itton
    -0.61
    ModLoader
    -0.60
     Crusade
    -0.59
     cardinal
    -0.59
    é¾
    -0.59
    200000
    -0.58
     RPC
    -0.58
     deviation
    -0.58
    POSITIVE LOGITS
    alian
    0.99
    hots
    0.90
    anthrop
    0.81
    uscript
    0.77
    =-=-=-=-
    0.75
    EMS
    0.74
    hood
    0.71
    olls
    0.70
    alties
    0.69
    reads
    0.69
    Activations Density 0.135%

    No Known Activations