© 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. 10-RES_POST_32K-OAI
    11. 29497
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate levels of peace of mind and security

    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
    608
    +0.13
    0.6%
    44
    +0.12
    0.6%
    756
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.13
    0.09
    608
    +0.12
    0.10
    362
    +0.12
    0.08
    Negative Logits
    hett
    -0.77
    raq
    -0.72
    Downloadha
    -0.69
    chester
    -0.68
    netflix
    -0.68
    ãģ®éŃĶ
    -0.67
    finals
    -0.67
     ILCS
    -0.66
    uel
    -0.65
    Enlarge
    -0.65
    POSITIVE LOGITS
     mind
    1.14
     spirit
    0.96
     circumstance
    0.96
     demeanor
    0.96
     manner
    0.96
     purpose
    0.93
     temperament
    0.93
     heart
    0.92
     disposition
    0.91
     tone
    0.91
    Activations Density 0.880%

    No Known Activations