© 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. 6005
    Prev
    Next
    INDEX
    Explanations

    references to physical keys and locks

    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
    189
    +0.11
    0.5%
    346
    +0.10
    0.5%
    35
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.11
    0.03
    435
    +0.10
    0.02
    678
    +0.09
    0.02
    Negative Logits
     Parish
    -0.71
    VS
    -0.69
    Bench
    -0.68
    Pierre
    -0.65
    isance
    -0.65
    VA
    -0.64
     Krish
    -0.64
    ctive
    -0.63
     Goods
    -0.63
    merce
    -0.62
    POSITIVE LOGITS
    stroke
    1.24
    codes
    0.95
    binding
    0.95
    bind
    0.89
    pressed
    0.89
    chain
    0.88
    pad
    0.87
    cases
    0.84
    */(
    0.84
    press
    0.83
    Activations Density 0.074%

    No Known Activations