© 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. 8-RES_POST_32K-OAI
    11. 5693
    Prev
    Next
    INDEX
    Explanations

    references to the name "Christ" and its variations

    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
    421
    +0.12
    0.6%
    314
    +0.12
    0.6%
    526
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.03
    421
    +0.12
    0.02
    224
    +0.11
    0.02
    Negative Logits
     Ammunition
    -0.68
    RECT
    -0.61
    quote
    -0.61
     Luxem
    -0.60
    6666
    -0.59
    TY
    -0.58
     Warrant
    -0.58
     derog
    -0.58
    heed
    -0.58
     Highlander
    -0.57
    POSITIVE LOGITS
    ophe
    1.45
    lia
    1.01
    offer
    1.00
    church
    1.00
    MAS
    0.98
    ophers
    0.95
    ensen
    0.95
    opher
    0.94
    oph
    0.94
    ina
    0.91
    Activations Density 0.072%

    No Known Activations