© 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. 30045
    Prev
    Next
    INDEX
    Explanations

    references to a collective group or individuals in contexts of opinion or belief

    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
    86
    +0.11
    0.5%
    631
    +0.11
    0.5%
    357
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    340
    +0.11
    0.05
    313
    +0.11
    0.04
    631
    +0.10
    0.04
    Negative Logits
    ipeg
    -0.72
    \/\/
    -0.70
    theless
    -0.67
    tainment
    -0.67
     VIDEOS
    -0.63
    ibal
    -0.62
     bindings
    -0.61
    ãģĨ
    -0.60
    rawdownloadcloneembedreportprint
    -0.59
    ukong
    -0.57
    POSITIVE LOGITS
     who
    1.28
     whose
    1.13
     whom
    1.11
     seeking
    1.05
     tasked
    1.02
     wishing
    1.01
     wielding
    0.98
     attempting
    0.97
    who
    0.96
     waging
    0.96
    Activations Density 0.124%

    No Known Activations