© 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. 10-RES_POST_32K-OAI
    11. 29660
    Prev
    Next
    INDEX
    Explanations

    phrases associated with financial investments and market transactions

    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
    480
    +0.10
    0.5%
    544
    +0.10
    0.5%
    282
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    435
    +0.10
    0.12
    288
    +0.10
    0.20
    575
    +0.09
    0.17
    Negative Logits
    rather
    -0.79
     Wrong
    -0.66
    instead
    -0.66
     Rather
    -0.64
     Stain
    -0.60
     SHARES
    -0.59
     NEVER
    -0.59
    uncture
    -0.58
    "]=>
    -0.58
     Never
    -0.56
    POSITIVE LOGITS
     thereafter
    1.07
     altogether
    1.04
     depending
    1.04
     later
    0.94
     apiece
    0.91
     totaling
    0.86
     further
    0.81
     each
    0.78
     afterwards
    0.78
     intermitt
    0.77
    Activations Density 5.182%

    No Known Activations