© 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. 5739
    Prev
    Next
    INDEX
    Explanations

    information related to salary trends and economic changes over time

    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
    151
    +0.09
    0.4%
    620
    +0.09
    0.4%
    23
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.09
    0.16
    490
    +0.09
    0.11
    650
    +0.08
    0.11
    Negative Logits
     assigned
    -0.86
     donated
    -0.83
     tasked
    -0.76
     consulted
    -0.76
     Donation
    -0.75
     allocated
    -0.74
     instructions
    -0.73
     volunteered
    -0.73
    cript
    -0.71
     assigning
    -0.70
    POSITIVE LOGITS
     slump
    1.23
     stagn
    1.14
     resurgence
    1.13
     resurg
    1.11
     breakout
    1.09
     surges
    1.06
     peaks
    1.04
     surge
    1.03
     momentum
    1.01
    luster
    1.01
    Activations Density 6.845%

    No Known Activations