© 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. 27620
    Prev
    Next
    INDEX
    Explanations

    pronouns and references to personal perspectives or opinions

    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
    383
    +0.10
    0.5%
    38
    +0.10
    0.4%
    515
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.10
    0.06
    361
    +0.10
    0.04
    715
    +0.09
    0.05
    Negative Logits
     beforehand
    -0.81
     initially
    -0.75
     currently
    -0.68
    mental
    -0.67
    ascript
    -0.65
     Initially
    -0.63
    cius
    -0.62
     meantime
    -0.61
     previous
    -0.61
     hitherto
    -0.60
    POSITIVE LOGITS
    here
    0.87
    nir
    0.69
    adays
    0.66
    amiliar
    0.64
    CLUS
    0.63
     reality
    0.61
     wondering
    0.61
     again
    0.60
     wonder
    0.59
     officially
    0.59
    Activations Density 1.160%

    No Known Activations