© 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. 6538
    Prev
    Next
    INDEX
    Explanations

    specific names and references to individuals or characters in various contexts

    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
    252
    +0.12
    0.6%
    218
    +0.10
    0.5%
    74
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.12
    0.12
    477
    +0.10
    0.08
    430
    +0.10
    0.14
    Negative Logits
     dub
    -0.67
     subdiv
    -0.65
     Mahjong
    -0.65
     calculate
    -0.64
     Want
    -0.60
     Wim
    -0.60
     noticing
    -0.60
     cram
    -0.60
     calculating
    -0.60
     Nanto
    -0.59
    POSITIVE LOGITS
     disappeared
    1.06
     vanished
    1.03
     remains
    0.96
     existed
    0.93
     disappears
    0.90
     survives
    0.88
     belongs
    0.85
     reapp
    0.84
     survived
    0.84
     belonged
    0.83
    Activations Density 2.107%

    No Known Activations