© 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. 31886
    Prev
    Next
    INDEX
    Explanations

    technical references and commands related to Java installation and version management

    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
    637
    +0.12
    0.5%
    713
    +0.10
    0.5%
    599
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.12
    435
    +0.10
    0.06
    255
    +0.10
    0.08
    Negative Logits
     Ukrainians
    -1.07
     Georgian
    -1.04
     Ukrainian
    -1.03
     Putin
    -1.00
    Ð
    -0.98
    Uk
    -0.98
    Georg
    -0.98
     fentanyl
    -0.97
     UKIP
    -0.96
    Ukraine
    -0.95
    POSITIVE LOGITS
     java
    1.93
     Java
    1.92
    java
    1.69
    Java
    1.59
     JD
    1.46
     Eclipse
    1.38
     Oracle
    1.34
    JD
    1.33
    jar
    1.28
     jar
    1.27
    Activations Density 1.952%

    No Known Activations