© 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 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. 30360
    Prev
    Next
    INDEX
    Explanations

    emotional and monetary appeals within the text

    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
    373
    +0.16
    0.7%
    459
    +0.10
    0.5%
    108
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.16
    0.05
    406
    +0.10
    0.06
    379
    +0.09
    0.06
    Negative Logits
     Afgh
    -0.81
     Machina
    -0.71
    stadt
    -0.69
    arten
    -0.69
    onite
    -0.68
    çīĪ
    -0.67
    ":""},{"
    -0.66
    tnc
    -0.63
    inventoryQuantity
    -0.62
     Sina
    -0.61
    POSITIVE LOGITS
    ket
    0.63
    oor
    0.61
    Eye
    0.59
    KEY
    0.59
    lip
    0.59
    oles
    0.58
    teen
    0.58
    t
    0.57
     CONTR
    0.57
    TN
    0.56
    Activations Density 0.449%

    No Known Activations