© 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. 7323
    Prev
    Next
    INDEX
    Explanations

    concepts related to personal growth and development of beliefs

    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
    80
    +0.10
    0.5%
    278
    +0.10
    0.4%
    565
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.10
    0.16
    750
    +0.10
    0.10
    665
    +0.10
    0.15
    Negative Logits
    isance
    -0.64
    ankind
    -0.62
    $.
    -0.61
     expired
    -0.60
    Applic
    -0.59
    winner
    -0.59
     expires
    -0.58
    estation
    -0.57
     awaited
    -0.57
     Sabha
    -0.56
    POSITIVE LOGITS
     alot
    1.04
     instinctively
    0.98
     unconsciously
    0.84
     subconscious
    0.81
     MUCH
    0.80
     quite
    0.80
     minded
    0.78
     consciously
    0.76
     pretty
    0.75
     LOT
    0.73
    Activations Density 3.390%

    No Known Activations