© 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. 3259
    Prev
    Next
    INDEX
    Explanations

    phrases relating to the concept of "medicalization" and its impacts

    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
    0.5%
    309
    +0.09
    0.4%
    636
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    549
    +0.12
    0.03
    309
    +0.09
    0.03
    636
    +0.08
    0.03
    Negative Logits
    rett
    -0.80
    RESULTS
    -0.77
    door
    -0.75
    NULL
    -0.70
    bos
    -0.70
    editor
    -0.67
    mail
    -0.67
    ĵĺ
    -0.67
    Wood
    -0.66
    Jon
    -0.65
    POSITIVE LOGITS
     indo
    0.70
     disadvant
    0.67
     Tibet
    0.67
    anmar
    0.65
    cius
    0.65
     fetish
    0.65
     anarch
    0.64
     monet
    0.64
     Zionism
    0.63
     communism
    0.63
    Activations Density 0.417%

    No Known Activations