© 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. 4682
    Prev
    Next
    INDEX
    Explanations

    references to the title "Dr." or mentions of doctors in general

    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
    683
    +0.10
    0.5%
    163
    +0.10
    0.4%
    671
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.10
    0.02
    683
    +0.10
    0.04
    176
    +0.09
    0.03
    Negative Logits
     Duo
    -0.81
     Leilan
    -0.76
     Intermediate
    -0.65
     Decay
    -0.62
     Mechdragon
    -0.62
    LOS
    -0.61
     Territories
    -0.61
     abound
    -0.58
    âĸĪ
    -0.57
     Homeland
    -0.56
    POSITIVE LOGITS
    agons
    1.38
    unk
    1.36
    inking
    1.33
    inker
    1.28
    inks
    1.24
    agging
    1.24
    agged
    1.20
    acon
    1.17
    ink
    1.14
    illing
    1.12
    Activations Density 0.080%

    No Known Activations