© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 5566
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    390
    +0.13
    0.6%
    373
    +0.12
    0.5%
    224
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.13
    -0.01
    537
    +0.12
    0.01
    314
    +0.10
    -0.01
    Negative Logits
    iston
    -0.67
     haun
    -0.65
    uyomi
    -0.65
     guiActiveUn
    -0.64
     Boe
    -0.64
     tram
    -0.62
    utral
    -0.62
     untreated
    -0.60
     gou
    -0.60
    ynes
    -0.59
    POSITIVE LOGITS
    HEAD
    0.77
    kernel
    0.76
    OTOS
    0.70
    REAM
    0.70
    CAR
    0.70
    LIN
    0.68
    lim
    0.66
    RED
    0.66
    TABLE
    0.66
    ENCY
    0.66
    Activations Density 0.054%

    No Known Activations