© 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. 27731
    Prev
    Next
    INDEX
    Explanations

    references to personal credibility and legitimacy within a competitive context

    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
    362
    +0.10
    0.5%
    459
    +0.09
    0.4%
    343
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.10
    608
    +0.09
    0.08
    15
    +0.09
    0.06
    Negative Logits
    yip
    -0.76
    opus
    -0.73
    rost
    -0.64
    uphem
    -0.64
    angel
    -0.64
     aloud
    -0.64
    atcher
    -0.64
    mill
    -0.64
     preferring
    -0.64
     Ambro
    -0.62
    POSITIVE LOGITS
     chances
    1.07
     credentials
    1.05
     reputation
    1.04
     image
    0.98
     credibility
    0.95
     chops
    0.92
     spirits
    0.92
     resolve
    0.91
     stature
    0.89
     position
    0.84
    Activations Density 0.812%

    No Known Activations