© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 5940
    Prev
    Next
    INDEX
    Explanations

    elements related to C and C++ programming syntax, particularly the structure of the "main" function

    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
    373
    +0.16
    0.7%
    314
    +0.12
    0.5%
    719
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.16
    0.04
    158
    +0.12
    0.03
    314
    +0.11
    0.00
    Negative Logits
    relations
    -0.80
     affinity
    -0.78
    worthiness
    -0.73
    arcity
    -0.72
     boundaries
    -0.72
     virginity
    -0.72
     thresholds
    -0.70
    alties
    -0.69
     locality
    -0.69
    osponsors
    -0.68
    POSITIVE LOGITS
    Loop
    0.87
    ¯¯¯¯
    0.73
    UFF
    0.73
    VPN
    0.73
    Running
    0.72
    ();
    0.72
     SDL
    0.72
    EGIN
    0.72
    ILD
    0.70
    ()
    0.69
    Activations Density 0.222%

    No Known Activations