© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 4561
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate time durations or spans

    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
    685
    +0.11
    0.5%
    599
    +0.10
    0.5%
    409
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.11
    0.06
    409
    +0.10
    0.04
    269
    +0.09
    0.04
    Negative Logits
    Lex
    -0.62
     grapp
    -0.60
    bye
    -0.59
     inev
    -0.59
    osite
    -0.59
    trak
    -0.58
    xs
    -0.57
    RAG
    -0.57
    OPA
    -0.56
    cca
    -0.56
    POSITIVE LOGITS
     period
    0.89
     span
    0.88
    period
    0.85
     timeframe
    0.84
     lifespan
    0.77
    ©¶æ¥µ
    0.76
     periods
    0.75
     range
    0.74
    arching
    0.73
     distances
    0.73
    Activations Density 0.378%

    No Known Activations