© 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. 8635
    Prev
    Next
    INDEX
    Explanations

    terms related to comparisons and contrasts 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
    197
    +0.11
    0.5%
    356
    +0.09
    0.4%
    509
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.11
    0.16
    540
    +0.09
    0.14
    650
    +0.09
    0.10
    Negative Logits
    /?
    -0.75
    spir
    -0.71
    lia
    -0.65
     calendars
    -0.64
    rams
    -0.63
    naire
    -0.62
    lio
    -0.62
     "#
    -0.62
    nan
    -0.61
    achusetts
    -0.60
    POSITIVE LOGITS
     shortcomings
    1.07
     disadvantages
    1.05
     drawbacks
    1.02
     drawback
    1.02
     disadvantage
    0.97
     flaws
    0.94
     caveats
    0.92
     nevertheless
    0.91
     downside
    0.91
     advantages
    0.89
    Activations Density 5.346%

    No Known Activations