© 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. 7307
    Prev
    Next
    INDEX
    Explanations

    references to casualties and humanitarian impacts in conflict situations

    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
    154
    +0.13
    0.6%
    555
    +0.09
    0.4%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    154
    +0.13
    0.13
    1
    +0.09
    0.08
    181
    +0.09
    0.10
    Negative Logits
     Edison
    -0.92
     Wilde
    -0.87
    Consumer
    -0.86
     Patent
    -0.82
    mson
    -0.80
     Einstein
    -0.79
     Invention
    -0.78
     Dickens
    -0.78
    mith
    -0.77
    geist
    -0.77
    POSITIVE LOGITS
     ceasefire
    1.27
     Houth
    1.26
     militants
    1.26
     rebel
    1.25
     rebels
    1.23
    zbollah
    1.23
     Syrian
    1.22
     jihadist
    1.22
     Kurdish
    1.21
     YPG
    1.21
    Activations Density 5.119%

    No Known Activations