© 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. 28167
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements and statistics related to various subjects

    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
    745
    +0.12
    0.5%
    256
    +0.10
    0.5%
    412
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.12
    0.07
    36
    +0.10
    0.08
    637
    +0.10
    0.05
    Negative Logits
    ONSORED
    -0.78
    ĪĴ
    -0.76
    VPN
    -0.72
    dit
    -0.71
    terday
    -0.70
    ulas
    -0.69
    kef
    -0.69
     "$:/
    -0.68
    yz
    -0.66
    Reloaded
    -0.64
    POSITIVE LOGITS
     lifespan
    1.13
     capacity
    1.06
     gross
    1.06
     total
    1.04
     circumference
    1.02
     maximum
    1.01
     expectancy
    0.98
     diameter
    0.98
     population
    0.96
     height
    0.96
    Activations Density 0.939%

    No Known Activations