© 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. 31688
    Prev
    Next
    INDEX
    Explanations

    comparative terms and concepts related to surpassing or outpacing others

    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
    750
    +0.13
    0.6%
    656
    +0.10
    0.5%
    418
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    750
    +0.13
    0.06
    269
    +0.10
    0.05
    647
    +0.10
    0.04
    Negative Logits
    ãĤ¹ãĥĪ
    -0.66
     encount
    -0.66
    leeve
    -0.66
    Different
    -0.64
     acknow
    -0.64
    cour
    -0.64
    iosyncr
    -0.64
    ahon
    -0.63
    Section
    -0.62
    tti
    -0.62
    POSITIVE LOGITS
     rivals
    1.01
     expectations
    0.99
     competitors
    0.98
     peers
    0.88
     rival
    0.83
     contemporaries
    0.83
     counterparts
    0.80
     others
    0.79
     opponents
    0.77
     fellow
    0.69
    Activations Density 0.765%

    No Known Activations