© 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. Attention Out - 32k
    9. 3-ATT_32K-OAI
    11. 3193
    Prev
    Next
    INDEX
    Explanations

    information related to events and registrations

    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
    71
    +0.15
    0.7%
    497
    +0.11
    0.5%
    745
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    202
    +0.15
    0.12
    245
    +0.11
    0.12
    74
    +0.10
    0.16
    Negative Logits
     helpless
    -0.78
    hoe
    -0.71
     articulate
    -0.68
    tnc
    -0.67
     breathing
    -0.65
    ek
    -0.65
    oxide
    -0.65
     wife
    -0.65
    iator
    -0.65
    roit
    -0.65
    POSITIVE LOGITS
    cember
    0.81
    BuyableInstoreAndOnline
    0.75
     editions
    0.75
    GMT
    0.73
     Ranked
    0.72
    ModLoader
    0.72
     Anniversary
    0.72
     subscriptions
    0.70
    Region
    0.70
    LCS
    0.69
    Activations Density 11.161%

    No Known Activations