© 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. 10-RES_POST_32K-OAI
    11. 26348
    Prev
    Next
    INDEX
    Explanations

    terms related to re-evaluation or reconsideration

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    665
    +0.18
    0.9%
    139
    +0.15
    0.7%
    49
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.18
    0.04
    22
    +0.15
    0.03
    389
    +0.13
    0.02
    Negative Logits
     wont
    -0.81
    IFIED
    -0.75
     dying
    -0.73
     tradem
    -0.72
     slowed
    -0.72
     reasoned
    -0.71
     yielded
    -0.71
     clenched
    -0.70
     passed
    -0.68
    ortunately
    -0.68
    POSITIVE LOGITS
    create
    1.12
    evaluate
    1.12
    enter
    1.11
    establish
    1.08
    route
    1.08
    animate
    1.06
    activate
    1.05
    fill
    1.03
    execute
    1.03
    send
    1.01
    Activations Density 0.112%

    No Known Activations