© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5780
    Prev
    Next
    INDEX
    Explanations

    legal codes and regulatory references

    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
    314
    +0.23
    1.1%
    316
    +0.12
    0.6%
    699
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.23
    0.00
    699
    +0.12
    0.01
    514
    +0.11
    0.01
    Negative Logits
     Nanto
    -0.73
     skewed
    -0.73
     Advertisement
    -0.69
     succession
    -0.66
    esses
    -0.65
     adm
    -0.65
     favour
    -0.63
     rem
    -0.62
    ously
    -0.62
     Tasman
    -0.62
    POSITIVE LOGITS
    §
    1.10
    ģ«
    0.93
    oral
    0.90
    Pg
    0.88
    english
    0.88
    DIV
    0.86
    668
    0.85
    RNA
    0.84
    ¹
    0.84
    740
    0.82
    Activations Density 0.031%

    No Known Activations