© 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. 8045
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize rescue, assistance, or social action organizations

    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
    241
    +0.14
    0.6%
    285
    +0.13
    0.6%
    314
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.14
    0.01
    232
    +0.13
    0.06
    140
    +0.13
    0.05
    Negative Logits
     awoken
    -0.70
     constitu
    -0.68
    opausal
    -0.66
     discovery
    -0.65
     quo
    -0.65
     distortion
    -0.64
     tom
    -0.64
    iologist
    -0.63
     resonance
    -0.63
     bottleneck
    -0.62
    POSITIVE LOGITS
     Your
    1.07
     Yourself
    1.05
    Your
    0.95
     Them
    0.92
     Away
    0.91
    ners
    0.86
    away
    0.85
     Me
    0.85
    your
    0.83
    Me
    0.81
    Activations Density 0.573%

    No Known Activations