© 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. 30392
    Prev
    Next
    INDEX
    Explanations

    expressions of positive news or favorable outcomes

    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
    428
    +0.12
    0.6%
    126
    +0.10
    0.5%
    7
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.12
    0.09
    428
    +0.10
    0.05
    159
    +0.10
    0.06
    Negative Logits
    friends
    -0.71
    anners
    -0.70
     Hebdo
    -0.70
    ãĥł
    -0.68
    ãĥ¼ãĤ¯
    -0.67
    agents
    -0.66
    NF
    -0.65
    Ts
    -0.65
    otypes
    -0.64
    oops
    -0.63
    POSITIVE LOGITS
     difference
    1.19
     overlap
    1.16
     reason
    1.16
     possibility
    1.08
     chance
    1.05
     discrepancy
    1.01
     downside
    0.96
     disparity
    0.95
     shortage
    0.94
     disagreement
    0.93
    Activations Density 0.821%

    No Known Activations