© 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. 3869
    Prev
    Next
    INDEX
    Explanations

    terms associated with national institutions or organizations

    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
    197
    +0.12
    0.5%
    648
    +0.10
    0.5%
    760
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    197
    +0.12
    0.03
    116
    +0.10
    0.02
    648
    +0.10
    0.03
    Negative Logits
    ÄŁ
    -0.78
    bye
    -0.72
    bars
    -0.69
    gob
    -0.69
    banks
    -0.68
    backs
    -0.66
    \/\/
    -0.64
     mids
    -0.63
    istered
    -0.63
    ibaba
    -0.62
    POSITIVE LOGITS
    ĺħ
    0.72
    ensical
    0.71
     conflic
    0.71
    CLASSIFIED
    0.69
    ailability
    0.66
    ĻĤ
    0.65
    actionDate
    0.64
     Appeal
    0.64
    ictionary
    0.63
    âĹ¼
    0.62
    Activations Density 0.094%

    No Known Activations