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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5445
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a greeting or welcome

    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
    +0.11
    0.5%
    454
    +0.11
    0.5%
    572
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.11
    0.03
    530
    +0.11
    0.02
    97
    +0.11
    0.01
    Negative Logits
    rings
    -0.67
    ebted
    -0.67
    soever
    -0.66
    matic
    -0.65
    matically
    -0.65
     emit
    -0.65
     actresses
    -0.63
    ingly
    -0.63
     exhibited
    -0.63
     convinc
    -0.62
    POSITIVE LOGITS
     Subtle
    0.91
     Paradise
    0.74
     Pirate
    0.72
     Jungle
    0.72
     Upper
    0.70
     Planet
    0.69
     Minute
    0.67
     paradise
    0.66
     Sunshine
    0.64
     Valhalla
    0.63
    Activations Density 0.189%

    No Known Activations