© 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. 7250
    Prev
    Next
    INDEX
    Explanations

    references to specific named entities, particularly characters or archetypes in narratives

    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
    25
    +0.11
    0.5%
    683
    +0.10
    0.5%
    583
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.01
    45
    +0.10
    0.01
    288
    +0.10
    0.01
    Negative Logits
    assi
    -0.73
    bing
    -0.65
    WB
    -0.60
    adan
    -0.58
    artifacts
    -0.57
    Rated
    -0.57
    skirts
    -0.56
    ograp
    -0.56
    adding
    -0.55
     Away
    -0.55
    POSITIVE LOGITS
    ãĥ´ãĤ¡
    1.00
    ãģ®éŃĶ
    0.96
    ãĥ»
    0.82
    ²¾
    0.81
    ç¥ŀ
    0.80
    inces
    0.75
    fire
    0.75
    enegger
    0.75
    PLIED
    0.74
     sidx
    0.72
    Activations Density 0.023%

    No Known Activations