© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Attention Out - 32k
    9. 3-ATT_32K-OAI
    11. 3946
    Prev
    Next
    INDEX
    Explanations

    references to the United States and its various entities, including governmental and geographical terms

    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
    615
    +0.11
    0.5%
    587
    +0.10
    0.5%
    606
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    587
    +0.11
    0.03
    642
    +0.10
    0.05
    615
    +0.10
    0.03
    Negative Logits
    idious
    -0.62
    ipel
    -0.62
    certain
    -0.61
    inction
    -0.61
     receptive
    -0.61
     slump
    -0.60
    osuke
    -0.59
    amount
    -0.59
    Shape
    -0.59
    ous
    -0.58
    POSITIVE LOGITS
     Agric
    0.68
    icent
    0.66
    dm
    0.66
     Ins
    0.65
    States
    0.64
     Definitions
    0.63
    states
    0.63
     Akron
    0.63
     1911
    0.62
     Citation
    0.61
    Activations Density 0.831%

    No Known Activations