© 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. 5718
    Prev
    Next
    INDEX
    Explanations

    terms related to economic costs and effectiveness

    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
    756
    +0.12
    0.5%
    558
    +0.11
    0.5%
    509
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.12
    0.12
    285
    +0.11
    0.04
    756
    +0.10
    -0.03
    Negative Logits
     greet
    -0.76
    waters
    -0.73
    obbies
    -0.69
    apons
    -0.67
    paio
    -0.65
    amiya
    -0.64
    itled
    -0.64
     chats
    -0.63
    ãĤ³
    -0.63
    icles
    -0.62
    POSITIVE LOGITS
     incurred
    1.06
    benefit
    0.93
    efficiency
    0.92
     taxpayers
    0.89
     prohib
    0.86
     Accounting
    0.86
     outweigh
    0.84
     feasibility
    0.82
     expenditure
    0.80
     profitability
    0.77
    Activations Density 1.899%

    No Known Activations