© 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. 10-RES_POST_32K-OAI
    11. 32146
    Prev
    Next
    INDEX
    Explanations

    variations of the suffix 'ner' across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    464
    +0.13
    0.6%
    419
    +0.13
    0.6%
    471
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.13
    -0.00
    659
    +0.13
    0.06
    284
    +0.11
    0.06
    Negative Logits
     depress
    -0.68
    rower
    -0.61
     disabling
    -0.61
    mble
    -0.61
     wiser
    -0.60
    ishers
    -0.58
     Header
    -0.57
     depth
    -0.56
     subconscious
    -0.56
    ener
    -0.56
    POSITIVE LOGITS
    omi
    0.85
    ho
    0.82
    hus
    0.79
    aki
    0.78
    ito
    0.77
    gie
    0.77
    ino
    0.75
    yth
    0.75
    elli
    0.73
    abad
    0.73
    Activations Density 0.897%

    No Known Activations