© 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. 3465
    Prev
    Next
    INDEX
    Explanations

    phrases related to events, relationships, or interactions in various contexts

    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
    373
    +0.13
    0.6%
    25
    +0.12
    0.6%
    120
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.13
    0.10
    224
    +0.12
    0.10
    581
    +0.11
    0.09
    Negative Logits
     cousin
    -0.72
     arsenal
    -0.70
     woes
    -0.69
     neighbors
    -0.68
     repertoire
    -0.68
     footprint
    -0.68
     partitions
    -0.64
     suite
    -0.64
     brethren
    -0.64
     counterpart
    -0.63
    POSITIVE LOGITS
    hurst
    0.76
    é¾
    0.70
    é»Ĵ
    0.68
    ichever
    0.67
    VERTIS
    0.66
    ividually
    0.66
     Horizon
    0.66
    omever
    0.65
    hovah
    0.64
    KK
    0.63
    Activations Density 17.081%

    No Known Activations