© 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. 30049
    Prev
    Next
    INDEX
    Explanations

    references to snow and its conditions

    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
    314
    +0.11
    0.5%
    385
    +0.11
    0.5%
    27
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.02
    27
    +0.11
    0.01
    129
    +0.10
    0.01
    Negative Logits
    ENTION
    -0.92
    ysis
    -0.88
    ISTER
    -0.73
     Jinn
    -0.71
    ister
    -0.66
    ########
    -0.65
    ostics
    -0.65
    YA
    -0.62
     NXT
    -0.62
    ention
    -0.62
    POSITIVE LOGITS
    flake
    1.73
    boarding
    1.26
    mobile
    1.20
    fall
    1.20
    storm
    1.08
    board
    1.07
    mob
    1.07
    banks
    1.06
    dr
    1.05
    balls
    1.04
    Activations Density 0.054%

    No Known Activations