© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Attention Out - 32k
    9. 3-ATT_32K-OAI
    11. 3093
    Prev
    Next
    INDEX
    Explanations

    references to government spending and fiscal policies

    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
    540
    +0.11
    0.5%
    248
    +0.11
    0.5%
    60
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    248
    +0.11
    0.03
    300
    +0.11
    0.03
    109
    +0.10
    0.03
    Negative Logits
    TY
    -0.80
     ancest
    -0.75
    ico
    -0.73
    assis
    -0.73
    ipp
    -0.71
    ape
    -0.70
    rait
    -0.70
    alez
    -0.69
     Droid
    -0.68
    inguished
    -0.67
    POSITIVE LOGITS
     discretionary
    0.76
    efficiency
    0.76
     quotas
    0.74
     quota
    0.71
     gimmick
    0.71
     bribe
    0.70
     allowance
    0.70
     dollars
    0.69
     bribes
    0.68
    ageddon
    0.68
    Activations Density 0.378%

    No Known Activations