© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3729
    Prev
    Next
    INDEX
    Explanations

    elements related to gaming mechanics and features

    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
    198
    +0.11
    0.5%
    459
    +0.11
    0.5%
    540
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.11
    0.10
    663
    +0.11
    0.10
    109
    +0.10
    0.05
    Negative Logits
    chin
    -0.96
    Ô
    -0.91
     cannabin
    -0.74
    paren
    -0.74
    cock
    -0.74
     modesty
    -0.73
     articulate
    -0.72
     horizont
    -0.72
    athing
    -0.70
     fluor
    -0.70
    POSITIVE LOGITS
     Reward
    0.78
     Rift
    0.77
     Calendar
    0.76
     Loot
    0.76
    Contents
    0.75
     NPCs
    0.75
     NPC
    0.74
     Credits
    0.72
     Rune
    0.72
    Players
    0.71
    Activations Density 9.106%

    No Known Activations