© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 3640
    Prev
    Next
    INDEX
    Explanations

    references to specific roles or job positions

    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
    692
    +0.14
    0.6%
    428
    +0.10
    0.4%
    458
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    415
    +0.14
    0.03
    291
    +0.10
    0.03
    316
    +0.10
    0.03
    Negative Logits
     Lent
    -0.74
    hawks
    -0.71
    acea
    -0.71
    Americ
    -0.67
     Liter
    -0.66
     Patron
    -0.66
    sonian
    -0.66
    atown
    -0.65
    Benz
    -0.65
    Champ
    -0.64
    POSITIVE LOGITS
    inctions
    0.83
    ANCE
    0.77
    aeper
    0.76
    Ü
    0.71
     clipboard
    0.70
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.69
    ENTS
    0.68
    ulty
    0.67
    ategories
    0.64
    ISO
    0.64
    Activations Density 1.295%

    No Known Activations