© 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 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. 30162
    Prev
    Next
    INDEX
    Explanations

    terms related to programming functions and methods

    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
    25
    +0.12
    0.6%
    326
    +0.12
    0.5%
    464
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.12
    0.08
    326
    +0.12
    0.07
    679
    +0.10
    0.08
    Negative Logits
    soType
    -0.85
    cellence
    -0.68
    itiveness
    -0.68
     Hare
    -0.67
     srfAttach
    -0.66
    etheless
    -0.65
    ItemThumbnailImage
    -0.64
    soDeliveryDate
    -0.63
    HER
    -0.61
     dedication
    -0.61
    POSITIVE LOGITS
     instruct
    1.02
     retrie
    1.01
     increments
    0.92
     converts
    0.91
     specifies
    0.85
     prints
    0.85
     extracts
    0.84
     stores
    0.83
     assigns
    0.81
     delet
    0.81
    Activations Density 0.532%

    No Known Activations