© 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. 5638
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 'P' in various contexts

    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
    314
    +0.14
    0.6%
    381
    +0.12
    0.6%
    145
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.09
    482
    +0.12
    0.08
    578
    +0.11
    0.07
    Negative Logits
     diplom
    -0.76
     bloom
    -0.67
     adm
    -0.65
     wip
    -0.64
     envy
    -0.62
     Rebels
    -0.60
     Magicka
    -0.59
     blo
    -0.59
     Dwar
    -0.59
     hairs
    -0.58
    POSITIVE LOGITS
    erenn
    0.97
    uls
    0.95
    TA
    0.93
    neum
    0.92
    icket
    0.91
    amph
    0.91
    redict
    0.90
    ivot
    0.89
    engu
    0.88
    raised
    0.88
    Activations Density 0.248%

    No Known Activations