© 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. 27993
    Prev
    Next
    INDEX
    Explanations

    concepts related to opposites and contrasts

    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
    555
    +0.12
    0.5%
    162
    +0.11
    0.5%
    301
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    555
    +0.12
    0.04
    232
    +0.11
    0.04
    167
    +0.10
    0.01
    Negative Logits
     Wol
    -0.63
     arc
    -0.61
     deviation
    -0.60
     pity
    -0.59
     crest
    -0.59
    chens
    -0.59
    ashtra
    -0.58
     Kubrick
    -0.58
     Gamble
    -0.57
     plat
    -0.57
    POSITIVE LOGITS
    itions
    1.81
    itional
    1.70
    itives
    1.46
    itors
    1.44
    itive
    1.44
    itiveness
    1.42
    itely
    1.39
    iting
    1.38
    ibles
    1.37
    ited
    1.36
    Activations Density 0.171%

    No Known Activations