© 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. 3273
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a shift or contrast in ideas or arguments

    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
    245
    +0.14
    0.6%
    700
    +0.11
    0.5%
    261
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    91
    +0.14
    0.04
    693
    +0.11
    0.03
    466
    +0.11
    0.03
    Negative Logits
     alright
    -0.65
    ogun
    -0.64
    amen
    -0.62
    las
    -0.61
    cheat
    -0.60
     veget
    -0.59
     crap
    -0.58
     mined
    -0.58
     leagues
    -0.58
    ecided
    -0.57
    POSITIVE LOGITS
    DragonMagazine
    0.74
    lihood
    0.67
    arity
    0.67
     Hof
    0.66
    ctory
    0.65
    gency
    0.63
    æĢ
    0.62
    ĨĴ
    0.62
     awaited
    0.61
     Polk
    0.61
    Activations Density 0.411%

    No Known Activations