© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 8138
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to legal documents and processes

    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
    31
    +0.17
    0.8%
    67
    +0.12
    0.5%
    536
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.17
    0.02
    232
    +0.12
    0.12
    503
    +0.10
    0.07
    Negative Logits
     dwarves
    -0.84
     doom
    -0.79
     crumble
    -0.77
    nuts
    -0.75
     orcs
    -0.75
    ĸļ
    -0.74
     Chaos
    -0.74
     circles
    -0.73
     bubbles
    -0.73
     mash
    -0.73
    POSITIVE LOGITS
    authorized
    1.12
    untary
    1.07
    Cert
    1.04
    utory
    1.01
     Applicant
    1.01
    visory
    1.01
     liability
    1.00
     Compliance
    0.97
    license
    0.97
    ailability
    0.96
    Activations Density 1.324%

    No Known Activations