© 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. 10-RES_POST_32K-OAI
    6. 29463
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" and phrases indicating sameness or consistency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    373
    +0.17
    0.8%
    473
    +0.13
    0.6%
    616
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.17
    0.05
    350
    +0.13
    0.04
    473
    +0.12
    0.03
    Negative Logits
    pee
    -0.79
     coffers
    -0.70
    artifacts
    -0.61
    hower
    -0.59
    tons
    -0.58
    ussia
    -0.58
     favour
    -0.56
     predic
    -0.56
     Gap
    -0.56
     dots
    -0.55
    POSITIVE LOGITS
     same
    0.91
     core
    0.79
    same
    0.68
    ohm
    0.68
    ysical
    0.68
     simplest
    0.67
     heart
    0.66
     minimum
    0.65
     essence
    0.65
     moment
    0.64
    Activations Density 0.451%

    No Known Activations