© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8072
    Prev
    Next
    INDEX
    Explanations

    instances of the word "was" 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
    744
    +0.10
    0.5%
    344
    +0.10
    0.4%
    314
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.10
    0.14
    102
    +0.10
    0.12
    7
    +0.09
    0.10
    Negative Logits
     disappearing
    -0.73
    ukong
    -0.68
     syndrome
    -0.67
    orem
    -0.66
     virginity
    -0.65
    Downloadha
    -0.65
    mma
    -0.64
     weed
    -0.64
    efined
    -0.63
    idence
    -0.63
    POSITIVE LOGITS
     headlined
    0.88
     scathing
    0.88
     reprinted
    0.77
     published
    0.76
     titled
    0.76
    itled
    0.75
     directed
    0.75
    ש
    0.75
     quoted
    0.74
    published
    0.70
    Activations Density 0.836%

    No Known Activations