© 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. 10-RES_POST_32K-OAI
    11. 29801
    Prev
    Next
    INDEX
    Explanations

    references to self-referential structures or instances in programming code

    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
    399
    +0.11
    0.5%
    96
    +0.10
    0.4%
    213
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    334
    +0.11
    0.01
    306
    +0.10
    0.02
    399
    +0.09
    0.01
    Negative Logits
    chery
    -0.80
    pher
    -0.75
    cock
    -0.71
    pora
    -0.67
    TING
    -0.67
    ËĪ
    -0.66
    grain
    -0.65
     Barcl
    -0.65
    ANCE
    -0.65
     Syndrome
    -0.64
    POSITIVE LOGITS
     ._
    0.86
     srf
    0.84
    userc
    0.77
     notify
    0.75
    ptr
    0.68
    ._
    0.64
     challeng
    0.62
     sidx
    0.61
     CONFIG
    0.59
    ::
    0.59
    Activations Density 0.137%

    No Known Activations