© 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. 8204
    Prev
    Next
    INDEX
    Explanations

    interpersonal relationships and connections

    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
    314
    +0.15
    0.7%
    218
    +0.14
    0.6%
    224
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.15
    0.13
    151
    +0.14
    0.10
    225
    +0.12
    0.08
    Negative Logits
     itself
    -0.71
     Viper
    -0.69
     convergence
    -0.65
    Quantity
    -0.62
     Dart
    -0.59
     Artemis
    -0.58
     ours
    -0.57
     phosphate
    -0.57
     Chimera
    -0.56
     Collider
    -0.56
    POSITIVE LOGITS
     whom
    1.14
    who
    0.97
    agher
    0.86
     who
    0.77
    igl
    0.70
     affection
    0.69
    oyal
    0.68
     uncond
    0.67
    ickr
    0.67
     emotionally
    0.66
    Activations Density 2.076%

    No Known Activations