© 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. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5738
    Prev
    Next
    INDEX
    Explanations

    characters or symbols, particularly in the context of programming or data representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    735
    +0.11
    0.5%
    703
    +0.11
    0.5%
    710
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.08
    314
    +0.11
    0.01
    57
    +0.10
    0.03
    Negative Logits
    azeera
    -1.00
    ascript
    -0.99
    kefeller
    -0.97
    uthor
    -0.96
    tein
    -0.96
    guyen
    -0.95
    asca
    -0.93
    ibaba
    -0.93
    lehem
    -0.90
    uce
    -0.90
    POSITIVE LOGITS
    Ble
    0.63
     Dana
    0.61
     society
    0.58
     Whitman
    0.58
    µ
    0.57
     remembered
    0.57
     victim
    0.57
    ł
    0.56
     tensions
    0.55
     goodwill
    0.55
    Activations Density 0.263%

    No Known Activations