© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 4098
    Prev
    Next
    INDEX
    Explanations

    significant mentions of economic terms or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-attn-out-SAEs/v5_32k_layer_3
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.3.hook_attn_out
    Hook Layer
    3
    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
    612
    +0.13
    0.6%
    481
    +0.13
    0.6%
    100
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    612
    +0.13
    0.11
    620
    +0.13
    0.10
    383
    +0.10
    0.10
    Negative Logits
     Glac
    -0.70
     Hedge
    -0.69
     Ripple
    -0.69
     Concent
    -0.68
     Conclusion
    -0.68
     Highlights
    -0.66
     Vessel
    -0.64
    ptoms
    -0.63
     Vulcan
    -0.62
     Waves
    -0.62
    POSITIVE LOGITS
    ©¶æ
    0.78
    ij士
    0.75
    oots
    0.71
    iggins
    0.70
    ascript
    0.66
    orum
    0.65
    ijn
    0.64
    ['
    0.62
    agna
    0.62
     hairs
    0.60
    Activations Density 13.307%

    No Known Activations