© 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. 7420
    Prev
    Next
    INDEX
    Explanations

    scientific concepts related to light and optics

    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
    678
    +0.16
    0.7%
    373
    +0.09
    0.4%
    268
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.16
    0.14
    570
    +0.09
    0.05
    647
    +0.09
    0.09
    Negative Logits
     Emblem
    -0.86
     Kids
    -0.85
     Citizenship
    -0.82
     Guatem
    -0.81
     Homeless
    -0.81
     Career
    -0.79
     Parents
    -0.79
     Families
    -0.78
     Achievements
    -0.78
     Millennials
    -0.76
    POSITIVE LOGITS
     electrons
    1.51
     wavelength
    1.39
     electromagnetic
    1.32
     wavelengths
    1.31
     photons
    1.29
     amplitude
    1.26
     emission
    1.26
     voltage
    1.26
     emitted
    1.24
     ions
    1.24
    Activations Density 3.229%

    No Known Activations