© 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. 3911
    Prev
    Next
    INDEX
    Explanations

    references to government departments and agencies

    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
    642
    +0.12
    0.6%
    31
    +0.10
    0.5%
    449
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.05
    146
    +0.10
    0.03
    91
    +0.10
    0.03
    Negative Logits
     Peb
    -0.69
     toast
    -0.67
     Lover
    -0.66
     embr
    -0.66
     rainbow
    -0.64
     mound
    -0.63
     WhatsApp
    -0.62
     victorious
    -0.62
     Reef
    -0.62
     Patriarch
    -0.62
    POSITIVE LOGITS
    bus
    0.81
    agents
    0.80
    arius
    0.78
    secret
    0.76
    pps
    0.74
    dq
    0.73
    rent
    0.71
    ngth
    0.70
     ..............
    0.70
    acci
    0.69
    Activations Density 1.195%

    No Known Activations