© 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. 7241
    Prev
    Next
    INDEX
    Explanations

    terms related to warfare and battle scenarios

    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
    +0.15
    0.7%
    408
    +0.10
    0.4%
    554
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.10
    575
    +0.10
    0.07
    325
    +0.09
    0.05
    Negative Logits
    wives
    -0.94
    pee
    -0.93
    chester
    -0.89
    gage
    -0.89
    aho
    -0.87
    lear
    -0.86
    lee
    -0.86
    omaly
    -0.85
    quer
    -0.85
    abet
    -0.84
    POSITIVE LOGITS
     computing
    0.66
     hots
    0.63
    vernment
    0.59
     shenan
    0.58
     dwell
    0.57
     sprink
    0.57
     wast
    0.56
     shortcut
    0.55
     allerg
    0.55
     augmented
    0.54
    Activations Density 0.545%

    No Known Activations