© 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. 4131
    Prev
    Next
    INDEX
    Explanations

    technical terminology and phrases related to technology and communication systems

    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
    171
    +0.12
    0.5%
    260
    +0.10
    0.5%
    40
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.12
    0.17
    341
    +0.10
    0.08
    478
    +0.10
    0.09
    Negative Logits
     alike
    -1.15
    aughed
    -0.64
     REL
    -0.62
     Leicester
    -0.62
     inflamm
    -0.62
     conclud
    -0.61
    20439
    -0.61
    arnaev
    -0.61
    )}
    -0.59
    é¾įåĸļ士
    -0.59
    POSITIVE LOGITS
    gain
    0.67
    bay
    0.65
    gap
    0.64
    redd
    0.63
    microsoft
    0.62
    iso
    0.61
     et
    0.60
    engine
    0.60
    scan
    0.59
    offset
    0.59
    Activations Density 7.355%

    No Known Activations