© 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. 3248
    Prev
    Next
    INDEX
    Explanations

    terms associated with animal behavior and health issues

    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
    11
    +0.11
    0.5%
    383
    +0.11
    0.5%
    174
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.11
    0.27
    65
    +0.11
    0.17
    1
    +0.10
    0.15
    Negative Logits
     manned
    -0.83
     administr
    -0.79
     legisl
    -0.79
     rul
    -0.77
     imposed
    -0.77
     bulldo
    -0.77
    ahime
    -0.75
     outlawed
    -0.75
    hement
    -0.75
     proposed
    -0.75
    POSITIVE LOGITS
    WN
    0.87
    Balt
    0.79
    ewitness
    0.74
    Eva
    0.72
    Joy
    0.71
    rums
    0.69
    arf
    0.69
    Counter
    0.68
    Jew
    0.68
    Merc
    0.68
    Activations Density 11.119%

    No Known Activations