© 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. 7396
    Prev
    Next
    INDEX
    Explanations

    phrases related to earning a living or financial stability

    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
    71
    +0.10
    0.5%
    129
    +0.10
    0.4%
    16
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    245
    +0.10
    0.04
    241
    +0.10
    0.03
    351
    +0.09
    0.03
    Negative Logits
    stanbul
    -0.71
     Matter
    -0.64
    osen
    -0.64
    hern
    -0.59
     Coun
    -0.59
     Metatron
    -0.58
    obyl
    -0.58
     Shiv
    -0.58
     Gaia
    -0.58
     Cardinal
    -0.58
    POSITIVE LOGITS
     exploiting
    0.94
     selling
    0.90
     handsome
    0.87
    paying
    0.81
    wage
    0.81
     profit
    0.79
     paycheck
    0.78
     exporting
    0.78
     income
    0.76
     Selling
    0.75
    Activations Density 0.303%

    No Known Activations