© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7238
    Prev
    Next
    INDEX
    Explanations

    negative sentiments related to experiences

    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
    767
    +0.10
    0.5%
    319
    +0.10
    0.4%
    61
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.10
    0.21
    718
    +0.10
    0.14
    8
    +0.10
    0.10
    Negative Logits
    xtap
    -0.73
     Baghd
    -0.66
     indistinguishable
    -0.66
    Cele
    -0.65
     celebr
    -0.64
    cele
    -0.64
    Beck
    -0.64
    steen
    -0.64
     celebrated
    -0.62
     Ballistic
    -0.61
    POSITIVE LOGITS
     Worse
    1.39
    Solution
    1.35
    Luckily
    1.25
     Luckily
    1.22
    Fortunately
    1.21
     Fortunately
    1.11
    Thankfully
    1.07
     worse
    1.06
     blame
    1.02
     unus
    1.01
    Activations Density 6.343%

    No Known Activations