© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29704
    Prev
    Next
    INDEX
    Explanations

    elements that indicate measurement, analysis, or categorization of data

    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
    551
    +0.25
    1.3%
    49
    +0.18
    0.9%
    139
    +0.17
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.25
    0.10
    540
    +0.18
    0.09
    189
    +0.17
    0.08
    Negative Logits
     adolesc
    -0.71
     preferring
    -0.70
     Likes
    -0.65
     Drops
    -0.63
    WithNo
    -0.63
    GGGGGGGG
    -0.63
    PDATE
    -0.63
     sleeping
    -0.62
    Magikarp
    -0.61
     favourites
    -0.61
    POSITIVE LOGITS
     showcase
    1.01
     offer
    1.00
     yield
    0.99
     guarantee
    0.99
     illustrate
    0.99
     remind
    0.98
     address
    0.98
     promise
    0.98
     highlight
    0.97
     serve
    0.97
    Activations Density 0.494%

    No Known Activations