© 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. 10-RES_POST_32K-OAI
    11. 26757
    Prev
    Next
    INDEX
    Explanations

    verbs indicating states or conditions, particularly in relation to individuals' sentiments and experiences

    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
    624
    +0.13
    0.6%
    69
    +0.12
    0.6%
    373
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.13
    0.12
    566
    +0.12
    0.10
    55
    +0.11
    0.11
    Negative Logits
     stated
    -0.78
    said
    -0.68
    say
    -0.62
    Appearances
    -0.60
     said
    -0.59
     prest
    -0.58
     Founders
    -0.58
     specified
    -0.58
     Plaint
    -0.57
     say
    -0.57
    POSITIVE LOGITS
     glad
    1.01
     unaware
    0.96
     grateful
    0.95
     sorry
    0.93
     surprised
    0.91
     thankful
    0.91
     astonished
    0.86
     unsure
    0.86
     amazed
    0.83
     disappointed
    0.82
    Activations Density 0.744%

    No Known Activations