© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8906
    Prev
    Next
    INDEX
    Explanations

    phrases related to products and their classifications

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    205
    +0.13
    0.6%
    753
    +0.11
    0.5%
    107
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.16
    16
    +0.11
    0.05
    205
    +0.10
    0.07
    Negative Logits
     earnest
    -0.68
     noises
    -0.64
    erest
    -0.63
     irregularities
    -0.61
     prostitutes
    -0.60
     apprehend
    -0.59
     interrupts
    -0.59
     sake
    -0.57
    zees
    -0.57
    CHAT
    -0.57
    POSITIVE LOGITS
     list
    1.80
    list
    1.45
     lists
    1.37
     repertoire
    1.29
    LIST
    1.27
     LIST
    1.27
     Lists
    1.26
     roster
    1.24
     List
    1.24
     lineup
    1.23
    Activations Density 4.388%

    No Known Activations