© 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. 7692
    Prev
    Next
    INDEX
    Explanations

    concepts related to opportunities and community engagement

    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
    634
    +0.12
    0.5%
    523
    +0.11
    0.5%
    365
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.11
    575
    +0.11
    0.08
    247
    +0.09
    0.06
    Negative Logits
    rez
    -0.89
    entious
    -0.76
     ãĤµ
    -0.74
    */(
    -0.73
    perature
    -0.71
    due
    -0.71
    lycer
    -0.71
    ysis
    -0.70
    ety
    -0.69
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.69
    POSITIVE LOGITS
     initiatives
    1.11
     programmes
    1.04
     programs
    1.04
     outreach
    1.01
     Programs
    1.01
     Advis
    1.00
     nonprofits
    0.89
     efforts
    0.89
     campaigns
    0.89
     agenda
    0.87
    Activations Density 0.790%

    No Known Activations