© 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. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 29644
    Prev
    Next
    INDEX
    Explanations

    geographical references to locations and regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    658
    +0.14
    0.6%
    409
    +0.11
    0.5%
    459
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    530
    +0.14
    0.03
    619
    +0.11
    0.03
    599
    +0.10
    0.03
    Negative Logits
    nces
    -0.71
    icho
    -0.69
    uala
    -0.66
    OFF
    -0.60
     Muse
    -0.59
     Akin
    -0.58
     Scient
    -0.58
     Cases
    -0.57
    achev
    -0.57
     Bulgar
    -0.57
    POSITIVE LOGITS
     board
    1.28
     aisle
    1.17
     spectrum
    1.11
     breadth
    0.96
    board
    0.94
     continuum
    0.93
     pond
    0.92
    Board
    0.91
     lifespan
    0.87
     boards
    0.86
    Activations Density 0.236%

    No Known Activations