© 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 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. 6494
    Prev
    Next
    INDEX
    Explanations

    phrases about positivity and enthusiasm towards 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
    606
    +0.14
    0.6%
    536
    +0.10
    0.5%
    267
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.14
    0.07
    102
    +0.10
    0.07
    55
    +0.09
    0.06
    Negative Logits
     withholding
    -0.68
     coerc
    -0.66
     pronoun
    -0.65
     withheld
    -0.64
     withhold
    -0.63
     contrace
    -0.62
     prosec
    -0.61
     filib
    -0.60
    nery
    -0.60
    UTERS
    -0.60
    POSITIVE LOGITS
    olor
    0.78
    orn
    0.77
    vez
    0.72
     needing
    0.70
    etheless
    0.64
    emin
    0.64
    irds
    0.64
    emale
    0.62
    asket
    0.62
    redits
    0.61
    Activations Density 0.260%

    No Known Activations