© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 4166
    Prev
    Next
    INDEX
    Explanations

    terms related to quarantine and medical treatment

    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
    575
    +0.13
    0.6%
    527
    +0.10
    0.5%
    232
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    490
    +0.13
    0.04
    452
    +0.10
    0.03
    547
    +0.10
    0.03
    Negative Logits
     aloud
    -0.78
     âĶľ
    -0.72
    --------------------------------------------------------
    -0.71
     supp
    -0.71
     frivol
    -0.69
     disappoint
    -0.69
     Slug
    -0.69
     ........
    -0.67
     Unloaded
    -0.64
    nings
    -0.64
    POSITIVE LOGITS
    bial
    0.80
     rare
    0.70
     Vall
    0.67
    oval
    0.65
    »Ĵ
    0.64
     Vault
    0.63
     Exclusive
    0.61
    visor
    0.61
    exclusive
    0.61
    rones
    0.60
    Activations Density 0.218%

    No Known Activations