© 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. 29232
    Prev
    Next
    INDEX
    Explanations

    terms associated with video editing software features and comparisons

    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
    588
    +0.14
    0.7%
    506
    +0.12
    0.6%
    115
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.19
    39
    +0.12
    0.13
    588
    +0.11
    0.13
    Negative Logits
    idium
    -0.81
     Hastings
    -0.80
     Sapp
    -0.80
    cephal
    -0.79
     Rath
    -0.79
     Jericho
    -0.79
     ringing
    -0.76
     curfew
    -0.73
     thyroid
    -0.72
    zbollah
    -0.72
    POSITIVE LOGITS
     Photoshop
    1.52
    Tool
    1.40
     Tools
    1.38
     workflow
    1.38
     Editing
    1.32
     tools
    1.31
     tool
    1.29
     Adobe
    1.29
    Tools
    1.28
     editing
    1.26
    Activations Density 4.029%

    No Known Activations