© 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. 8-RES_POST_32K-OAI
    11. 5948
    Prev
    Next
    INDEX
    Explanations

    elements indicating product quality and customer satisfaction

    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
    20
    +0.10
    0.5%
    180
    +0.10
    0.5%
    687
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.10
    0.07
    246
    +0.10
    0.05
    652
    +0.09
    0.04
    Negative Logits
    BBC
    -0.82
    yip
    -0.81
    obook
    -0.81
     Flavoring
    -0.77
    usterity
    -0.73
    Newsletter
    -0.72
    CTV
    -0.70
    irtual
    -0.68
     Kafka
    -0.66
     Protestants
    -0.66
    POSITIVE LOGITS
     tha
    1.35
     fuckin
    1.28
    izzle
    1.19
    itiz
    1.04
     ta
    1.02
     dat
    0.95
     asses
    0.95
    \\
    0.91
     includ
    0.90
     lil
    0.89
    Activations Density 1.444%

    No Known Activations