© 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. 31143
    Prev
    Next
    INDEX
    Explanations

    mentions of growth, development, and trends in various sectors and policies

    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
    495
    +0.11
    0.5%
    215
    +0.10
    0.5%
    365
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.21
    225
    +0.10
    0.16
    724
    +0.10
    0.18
    Negative Logits
     Anon
    -0.76
    interstitial
    -0.71
    theless
    -0.67
    paio
    -0.65
     Piercing
    -0.64
    alloween
    -0.63
     manslaughter
    -0.61
    Downloadha
    -0.61
    irlf
    -0.60
    onement
    -0.59
    POSITIVE LOGITS
     arsenal
    1.29
     pathway
    1.27
     landscape
    1.26
     repertoire
    1.25
     trajectory
    1.23
     regime
    1.23
     regimen
    1.22
     system
    1.22
     framework
    1.22
     environment
    1.20
    Activations Density 2.811%

    No Known Activations