© 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. 29949
    Prev
    Next
    INDEX
    Explanations

    references to religious texts and figures, particularly within Islam

    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
    373
    +0.15
    0.7%
    662
    +0.12
    0.6%
    383
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.15
    0.03
    232
    +0.12
    0.03
    373
    +0.11
    -0.03
    Negative Logits
     Reincarn
    -0.85
    heit
    -0.80
    SPONSORED
    -0.78
    astical
    -0.67
     heresy
    -0.67
    christ
    -0.67
     Sharia
    -0.66
     Cth
    -0.64
     faiths
    -0.64
     atheism
    -0.64
    POSITIVE LOGITS
     bin
    0.84
    dullah
    0.76
    ager
    0.68
     Narr
    0.67
    anza
    0.66
    ifa
    0.66
     McCartney
    0.64
    itta
    0.64
    rio
    0.64
    aged
    0.64
    Activations Density 0.320%

    No Known Activations