© 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. 4093
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to brands or companies, particularly those beginning with "Ab"

    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
    459
    +0.11
    0.5%
    30
    +0.10
    0.5%
    150
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    521
    +0.11
    0.02
    46
    +0.10
    0.02
    441
    +0.09
    0.02
    Negative Logits
     acad
    -0.74
    opers
    -0.67
    houses
    -0.67
    olars
    -0.66
    interstitial
    -0.66
     cones
    -0.66
    sylv
    -0.64
     colleg
    -0.63
     previews
    -0.62
     pools
    -0.61
    POSITIVE LOGITS
    EVA
    0.90
     Wonderland
    0.79
    querque
    0.79
    Ö¼
    0.73
    ardless
    0.71
     Verse
    0.71
    vez
    0.69
    eri
    0.68
    itely
    0.67
    Uncommon
    0.66
    Activations Density 0.847%

    No Known Activations