© 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. 8973
    Prev
    Next
    INDEX
    Explanations

    terms related to the physiological effects of substances and their definitions

    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
    70
    +0.10
    0.5%
    600
    +0.09
    0.4%
    594
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    647
    +0.10
    0.07
    268
    +0.09
    0.02
    598
    +0.09
    0.04
    Negative Logits
     Hort
    -0.68
    ··
    -0.66
     Rapp
    -0.66
    daq
    -0.61
     showc
    -0.59
     Angola
    -0.58
     Takeru
    -0.58
     Ranger
    -0.58
    icide
    -0.57
     Hib
    -0.57
    POSITIVE LOGITS
     whereby
    0.84
     shorthand
    0.79
     grouping
    0.78
     abbre
    0.77
     Definition
    0.72
    those
    0.70
     refers
    0.70
     term
    0.69
     acronym
    0.68
    meaning
    0.68
    Activations Density 3.322%

    No Known Activations