© 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. 10-RES_POST_32K-OAI
    11. 30331
    Prev
    Next
    INDEX
    Explanations

    references to government entities and officials

    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
    751
    +0.12
    0.6%
    300
    +0.10
    0.5%
    502
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.12
    0.11
    224
    +0.10
    0.10
    139
    +0.10
    0.10
    Negative Logits
    Occ
    -0.69
     Opera
    -0.68
     Alright
    -0.65
    Story
    -0.65
    Newsletter
    -0.64
    Interstitial
    -0.64
     foll
    -0.63
     Harbour
    -0.61
    kB
    -0.61
    Thread
    -0.61
    POSITIVE LOGITS
     insisted
    0.83
     revealed
    0.82
     branded
    0.78
     claimed
    0.75
     admitted
    0.74
     denied
    0.71
     MP
    0.68
     accused
    0.67
     deny
    0.67
    arted
    0.67
    Activations Density 1.127%

    No Known Activations