© 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 EvalsExportsinterp-engineNEWAPI 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. 31704
    Prev
    Next
    INDEX
    Explanations

    references to economic decline, particularly related to recessions and their implications

    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
    218
    +0.11
    0.5%
    608
    +0.10
    0.5%
    453
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.11
    0.10
    123
    +0.10
    0.09
    172
    +0.09
    0.04
    Negative Logits
    quartered
    -0.67
     Norn
    -0.66
     Engineers
    -0.65
    UFC
    -0.64
     Tire
    -0.64
     congr
    -0.59
    Score
    -0.59
     Wrest
    -0.58
     pumps
    -0.57
     Able
    -0.57
    POSITIVE LOGITS
     stagnation
    0.94
     obscurity
    0.93
     anarchy
    0.92
    essim
    0.92
     unch
    0.90
     adolescence
    0.88
     saturation
    0.84
     recession
    0.84
     chaos
    0.84
     decline
    0.84
    Activations Density 0.836%

    No Known Activations