© 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. 10-RES_POST_32K-OAI
    11. 29452
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate relationships or connections between entities

    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
    59
    +0.10
    0.5%
    391
    +0.10
    0.4%
    580
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.10
    0.12
    362
    +0.10
    0.10
    22
    +0.09
    0.07
    Negative Logits
    NING
    -0.71
    76561
    -0.70
     è£ıè¦ļéĨĴ
    -0.69
     mathemat
    -0.66
     Canter
    -0.63
     regards
    -0.62
     likened
    -0.61
     Winc
    -0.60
     uttered
    -0.60
     clicked
    -0.59
    POSITIVE LOGITS
    ordinate
    0.79
    anz
    0.79
    effic
    0.73
    vv
    0.72
    coming
    0.71
    osponsors
    0.71
    ste
    0.67
    missions
    0.67
    adr
    0.67
    bread
    0.67
    Activations Density 1.163%

    No Known Activations