© 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. 4632
    Prev
    Next
    INDEX
    Explanations

    terms related to emotions and states of being

    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
    297
    +0.10
    0.4%
    504
    +0.10
    0.4%
    314
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.08
    288
    +0.10
    0.09
    326
    +0.09
    0.07
    Negative Logits
    perature
    -0.68
     nit
    -0.66
    bably
    -0.66
     peanuts
    -0.63
     toget
    -0.60
     shorthand
    -0.60
     curb
    -0.60
    coon
    -0.59
     groceries
    -0.59
     referen
    -0.57
    POSITIVE LOGITS
    breaker
    1.09
    bringer
    1.06
     Of
    1.06
     Reborn
    0.99
    Of
    0.99
    oft
    0.99
    ful
    0.97
    breakers
    0.94
    seekers
    0.93
    bolt
    0.89
    Activations Density 0.746%

    No Known Activations