© 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 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. 28530
    Prev
    Next
    INDEX
    Explanations

    recurrent mentions of the pronoun "I" and related personal expressions

    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
    36
    +0.11
    0.5%
    191
    +0.11
    0.5%
    173
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.11
    0.21
    354
    +0.11
    0.18
    551
    +0.10
    0.18
    Negative Logits
    naire
    -0.80
    nell
    -0.78
    nel
    -0.70
    employed
    -0.66
    aunder
    -0.65
    jiang
    -0.65
    affiliated
    -0.65
    umerous
    -0.64
    Registered
    -0.64
    outine
    -0.63
    POSITIVE LOGITS
     guess
    0.99
     dig
    0.97
     reckon
    0.97
     dunno
    0.85
     think
    0.85
     wanna
    0.84
     suppose
    0.80
     dare
    0.77
     assure
    0.77
     gotta
    0.76
    Activations Density 1.078%

    No Known Activations