© 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. 10-RES_POST_32K-OAI
    11. 26809
    Prev
    Next
    INDEX
    Explanations

    events involving damage or disasters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    666
    +0.12
    0.5%
    753
    +0.11
    0.5%
    689
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.12
    0.07
    260
    +0.11
    0.08
    335
    +0.10
    0.05
    Negative Logits
    Tea
    -0.80
    HCR
    -0.78
    arte
    -0.75
     abstinence
    -0.75
    ĸļ
    -0.74
     persuasion
    -0.70
     Arpaio
    -0.70
     festivals
    -0.69
    asks
    -0.69
     petitions
    -0.69
    POSITIVE LOGITS
     debris
    1.31
     wreckage
    1.28
     toppled
    1.21
     crashing
    1.19
     crashed
    1.18
     collapsed
    1.17
     collapse
    1.17
     collided
    1.15
     collapses
    1.14
     crash
    1.14
    Activations Density 2.072%

    No Known Activations