© 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. 4211
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and organizations

    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
    756
    +0.14
    0.7%
    497
    +0.14
    0.7%
    420
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    297
    +0.14
    0.09
    518
    +0.14
    0.10
    659
    +0.13
    0.09
    Negative Logits
     ACTIONS
    -0.74
    RPG
    -0.67
     Ideas
    -0.66
     Rivals
    -0.65
     REL
    -0.61
     Doctrine
    -0.59
     pund
    -0.59
     Warfare
    -0.59
    ----------------------------------------------------------------
    -0.58
    QUEST
    -0.58
    POSITIVE LOGITS
    gemony
    0.78
    ngth
    0.74
    amins
    0.71
    chev
    0.69
    imura
    0.68
    enburg
    0.67
    sheets
    0.67
    ffe
    0.67
    verning
    0.67
    selage
    0.66
    Activations Density 3.678%

    No Known Activations