© 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. 3346
    Prev
    Next
    INDEX
    Explanations

    references to locations and actions related to moving or changing state

    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
    71
    +0.15
    0.7%
    722
    +0.10
    0.5%
    307
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    587
    +0.15
    0.07
    636
    +0.10
    0.06
    528
    +0.09
    0.12
    Negative Logits
    writers
    -0.66
    hent
    -0.64
    Fox
    -0.63
    Dem
    -0.63
     heels
    -0.61
    ogan
    -0.61
    demon
    -0.58
    alt
    -0.58
    rollers
    -0.57
    Times
    -0.57
    POSITIVE LOGITS
     arrang
    0.90
     agre
    0.84
     awa
    0.76
     anew
    0.70
    staking
    0.68
     proble
    0.67
    uala
    0.67
     unemploy
    0.66
     appre
    0.65
     recip
    0.64
    Activations Density 4.096%

    No Known Activations