© 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. 29339
    Prev
    Next
    INDEX
    Explanations

    references to the Mandela Effect and its impact on perception

    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
    232
    +0.19
    0.9%
    699
    +0.14
    0.6%
    145
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    530
    +0.19
    0.09
    326
    +0.14
    0.05
    699
    +0.12
    0.04
    Negative Logits
    RAY
    -0.96
    jri
    -0.91
     behavi
    -0.88
    quickShipAvailable
    -0.87
    ItemThumbnailImage
    -0.86
    OUNT
    -0.86
    END
    -0.84
    DERR
    -0.84
    DEN
    -0.83
    ARE
    -0.81
    POSITIVE LOGITS
     A
    0.98
     Photograph
    0.94
     EXP
    0.89
     P
    0.89
     M
    0.88
     C
    0.88
     ARTICLE
    0.88
     S
    0.87
     D
    0.87
     F
    0.87
    Activations Density 0.231%

    No Known Activations