© 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. 29462
    Prev
    Next
    INDEX
    Explanations

    references to missing persons and their related cases

    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
    494
    +0.13
    0.6%
    8
    +0.10
    0.5%
    392
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.13
    0.15
    494
    +0.10
    0.09
    537
    +0.10
    0.08
    Negative Logits
    ħĭ
    -0.87
     spons
    -0.81
     tiers
    -0.80
     synerg
    -0.78
    galitarian
    -0.78
     Consent
    -0.77
     Democr
    -0.77
     applause
    -0.77
     applaud
    -0.71
     clauses
    -0.70
    POSITIVE LOGITS
     vanished
    1.58
     disappearance
    1.51
     disappeared
    1.47
     sightings
    1.42
     whereabouts
    1.35
     disappear
    1.32
     vanish
    1.30
     sighting
    1.26
     disappearing
    1.24
     vanishing
    1.24
    Activations Density 5.647%

    No Known Activations