© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 29562
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and references to responsibility or accountability in actions

    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
    477
    +0.13
    0.6%
    454
    +0.12
    0.5%
    474
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.13
    0.19
    551
    +0.12
    0.16
    354
    +0.10
    0.15
    Negative Logits
    urred
    -0.59
    issors
    -0.57
    adj
    -0.57
    Basic
    -0.56
    vous
    -0.56
    REE
    -0.55
    ippery
    -0.55
     TheNitromeFan
    -0.54
    fx
    -0.54
    hatt
    -0.54
    POSITIVE LOGITS
     somehow
    1.12
     oneself
    0.89
     personally
    0.87
     herself
    0.86
     ourselves
    0.86
     yourselves
    0.85
     myself
    0.84
     themselves
    0.84
    ,—
    0.81
     purposefully
    0.76
    Activations Density 1.552%

    No Known Activations