© 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. 26793
    Prev
    Next
    INDEX
    Explanations

    references to authority, obedience, and adherence to rules or doctrines

    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
    265
    +0.11
    0.5%
    25
    +0.11
    0.5%
    283
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.11
    0.10
    608
    +0.11
    0.09
    385
    +0.10
    0.06
    Negative Logits
    anwhile
    -0.70
    paren
    -0.69
    itivity
    -0.68
    Reviewer
    -0.67
     Ambrose
    -0.64
    uria
    -0.64
     Investigations
    -0.63
    afety
    -0.63
    enaries
    -0.63
    pora
    -0.61
    POSITIVE LOGITS
     dictates
    1.49
     wishes
    1.27
     commands
    1.27
     whims
    1.27
     whim
    1.23
     orders
    1.15
     dictate
    1.09
     impulses
    1.08
     urges
    1.06
     directives
    1.03
    Activations Density 1.171%

    No Known Activations