© 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 EvalsExportsAPI 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. 30931
    Prev
    Next
    INDEX
    Explanations

    phrases related to motivations or intentions behind actions

    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
    700
    +0.10
    0.5%
    282
    +0.10
    0.4%
    730
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.10
    0.15
    665
    +0.10
    0.14
    139
    +0.09
    0.13
    Negative Logits
    sbm
    -0.71
     defaults
    -0.59
    xit
    -0.58
     trillions
    -0.58
    intent
    -0.57
    ona
    -0.57
     Pref
    -0.57
     Favorite
    -0.56
    dom
    -0.56
     DRAG
    -0.56
    POSITIVE LOGITS
     amuse
    1.02
     amusement
    0.98
     illustrate
    0.91
     distract
    0.89
     underscore
    0.88
    arrass
    0.85
     appease
    0.84
     deterrence
    0.84
     relieve
    0.84
     reassure
    0.82
    Activations Density 0.750%

    No Known Activations