© 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. 7783
    Prev
    Next
    INDEX
    Explanations

    references to administrative actions and personnel changes within organizations

    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
    146
    +0.10
    0.5%
    679
    +0.10
    0.4%
    189
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.10
    0.13
    86
    +0.10
    0.08
    566
    +0.09
    0.09
    Negative Logits
    çķ
    -0.83
    jug
    -0.77
     neighbour
    -0.73
     Chaser
    -0.73
    yz
    -0.69
     Bolt
    -0.68
     Varg
    -0.67
     neighbor
    -0.65
    itars
    -0.65
     rebound
    -0.64
    POSITIVE LOGITS
     resigned
    1.01
     resign
    0.99
     assassinated
    0.90
     vested
    0.80
     overseeing
    0.79
     Cosponsors
    0.78
     salaries
    0.78
     memo
    0.77
     Salary
    0.76
     testify
    0.73
    Activations Density 4.340%

    No Known Activations