© 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. 10-RES_POST_32K-OAI
    11. 27837
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "in" and its context throughout the text

    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
    676
    +0.12
    0.5%
    29
    +0.11
    0.5%
    82
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.12
    0.10
    29
    +0.11
    0.08
    469
    +0.10
    0.06
    Negative Logits
    QL
    -0.64
    anship
    -0.57
     followed
    -0.57
    iasm
    -0.57
     observes
    -0.57
     informed
    -0.56
     characterized
    -0.55
     redes
    -0.55
    DEM
    -0.55
     Leilan
    -0.55
    POSITIVE LOGITS
     storage
    1.00
     circulation
    0.93
     cabinets
    0.89
     drawer
    0.89
     crates
    0.87
     jars
    0.86
     bags
    0.85
     hand
    0.83
    storage
    0.81
     possession
    0.80
    Activations Density 0.388%

    No Known Activations