© 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. 29318
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives

    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
    216
    +0.12
    0.5%
    194
    +0.12
    0.5%
    19
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.12
    0.01
    216
    +0.12
    0.01
    659
    +0.12
    0.01
    Negative Logits
     incorpor
    -0.68
     impe
    -0.66
     Indones
    -0.60
     faculties
    -0.59
    teenth
    -0.59
     tremend
    -0.57
    perty
    -0.57
     empt
    -0.56
     Corker
    -0.56
     nanop
    -0.55
    POSITIVE LOGITS
    imate
    1.20
    ruct
    1.17
    oppers
    1.10
    imating
    1.09
    imates
    1.08
    reet
    1.06
    ruck
    1.06
    hetically
    1.05
    imated
    1.05
    ream
    1.05
    Activations Density 0.087%

    No Known Activations