© 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. 29576
    Prev
    Next
    INDEX
    Explanations

    phrases related to trends and future predictions

    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
    702
    +0.13
    0.6%
    8
    +0.10
    0.5%
    275
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.19
    608
    +0.10
    0.18
    393
    +0.10
    0.14
    Negative Logits
    ĸļ
    -0.77
    iuses
    -0.70
    @#&
    -0.69
     metic
    -0.67
    umbnails
    -0.63
     froze
    -0.61
    ļéĨĴ
    -0.61
    racuse
    -0.60
    ioch
    -0.59
    affe
    -0.58
    POSITIVE LOGITS
     future
    1.77
     foreseeable
    1.56
     2019
    1.48
     2020
    1.47
     someday
    1.46
     upcoming
    1.45
     forthcoming
    1.45
     tomorrow
    1.44
    future
    1.43
     2021
    1.42
    Activations Density 2.738%

    No Known Activations