© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 4384
    Prev
    Next
    INDEX
    Explanations

    numbers and references to sizes or weights associated with individuals

    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
    420
    +0.13
    0.6%
    384
    +0.10
    0.5%
    359
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.13
    0.09
    562
    +0.10
    0.11
    387
    +0.10
    0.12
    Negative Logits
    Aust
    -0.75
    Development
    -0.71
     Carey
    -0.68
    ellar
    -0.67
    ellen
    -0.64
    jar
    -0.64
     Miko
    -0.64
    ante
    -0.63
    Lago
    -0.63
     reins
    -0.63
    POSITIVE LOGITS
     ripple
    0.71
    wick
    0.70
     voic
    0.69
     horizont
    0.64
     inconvenience
    0.63
     msec
    0.63
     dysph
    0.62
     inex
    0.61
     Impl
    0.61
     oppression
    0.61
    Activations Density 24.206%

    No Known Activations