© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 26910
    Prev
    Next
    INDEX
    Explanations

    references to legal agreements and contracts

    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
    500
    +0.15
    0.7%
    240
    +0.11
    0.5%
    215
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    500
    +0.15
    0.08
    756
    +0.11
    -0.01
    679
    +0.10
    0.12
    Negative Logits
    ideshow
    -0.82
    population
    -0.80
    nces
    -0.77
     Beir
    -0.77
    Naz
    -0.72
    roller
    -0.71
     Appalach
    -0.71
    esity
    -0.71
    chester
    -0.69
    ugen
    -0.68
    POSITIVE LOGITS
     contract
    2.01
     contracts
    2.00
     Contracts
    1.86
    contract
    1.85
     contractual
    1.83
     agreements
    1.80
    Contract
    1.79
     Contract
    1.73
     agreement
    1.63
     renegoti
    1.59
    Activations Density 3.408%

    No Known Activations