© 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. 3798
    Prev
    Next
    INDEX
    Explanations

    references to individuals named Patrick 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
    452
    +0.12
    0.5%
    683
    +0.10
    0.5%
    92
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    452
    +0.12
    0.04
    659
    +0.10
    0.04
    314
    +0.10
    0.03
    Negative Logits
    objects
    -0.66
    Offset
    -0.65
    Org
    -0.64
    Clock
    -0.63
    Catalog
    -0.61
    ructure
    -0.61
     Cache
    -0.61
    renches
    -0.60
     Reson
    -0.59
    URRENT
    -0.59
    POSITIVE LOGITS
     Whis
    0.68
     NX
    0.64
    ega
    0.62
     Pearce
    0.60
    */(
    0.60
    kov
    0.58
     <+
    0.57
     Generations
    0.57
    eve
    0.57
     Honour
    0.56
    Activations Density 0.651%

    No Known Activations