© 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. 4667
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Soon" indicating the passage of time or the anticipation of future events

    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
    98
    +0.10
    0.5%
    314
    +0.10
    0.5%
    144
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    144
    +0.10
    0.03
    98
    +0.10
    0.03
    760
    +0.10
    0.02
    Negative Logits
    utenberg
    -0.68
     CODE
    -0.68
    ocker
    -0.64
     psy
    -0.60
     VIDEOS
    -0.60
    CD
    -0.58
    BIP
    -0.55
    cart
    -0.54
     immersion
    -0.53
     roller
    -0.52
    POSITIVE LOGITS
     enough
    0.98
     thereafter
    0.87
     Enough
    0.82
    orthy
    0.78
    est
    0.77
    eteenth
    0.77
     afterwards
    0.76
     afterward
    0.74
    enough
    0.70
    ons
    0.69
    Activations Density 0.058%

    No Known Activations