© 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. 27270
    Prev
    Next
    INDEX
    Explanations

    phrases related to occurrences and instances in time and location

    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
    362
    +0.11
    0.5%
    268
    +0.10
    0.4%
    730
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.11
    0.20
    608
    +0.10
    0.17
    22
    +0.09
    0.10
    Negative Logits
    iction
    -0.65
    cussion
    -0.64
    swer
    -0.61
     improves
    -0.59
     relies
    -0.59
     risked
    -0.56
     featuring
    -0.56
    urden
    -0.56
     incorporating
    -0.55
    ocating
    -0.55
    POSITIVE LOGITS
     nowhere
    1.03
     somewhere
    0.88
    actly
    0.88
     exactly
    0.87
     precisely
    0.85
     separate
    0.83
     only
    0.82
     distinct
    0.81
     opposite
    0.79
     roughly
    0.76
    Activations Density 2.445%

    No Known Activations