© 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. 7359
    Prev
    Next
    INDEX
    Explanations

    references to factories and industrial settings

    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
    288
    +0.14
    0.7%
    212
    +0.13
    0.6%
    167
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.02
    459
    +0.13
    0.01
    652
    +0.12
    0.01
    Negative Logits
    soever
    -0.85
    laus
    -0.74
    byss
    -0.73
    meet
    -0.69
    vind
    -0.68
    MENTS
    -0.67
    CHAT
    -0.66
    ï¸
    -0.65
    nir
    -0.65
    kj
    -0.64
    POSITIVE LOGITS
    ounter
    0.84
    actory
    0.78
    Made
    0.77
    orer
    0.77
    orde
    0.76
     reset
    0.73
    places
    0.72
    asted
    0.71
     farming
    0.70
    arded
    0.69
    Activations Density 0.039%

    No Known Activations