© 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 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. 28309
    Prev
    Next
    INDEX
    Explanations

    references to specific projects and their management details

    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
    409
    +0.11
    0.5%
    766
    +0.11
    0.5%
    185
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.11
    0.01
    504
    +0.11
    0.04
    632
    +0.11
    0.04
    Negative Logits
     Coulter
    -0.85
     Barber
    -0.83
     Bulg
    -0.83
    Sher
    -0.82
     Hannity
    -0.78
     supermarkets
    -0.75
     etiquette
    -0.72
     seasoning
    -0.71
     sweets
    -0.70
     chains
    -0.70
    POSITIVE LOGITS
    Project
    2.31
     Project
    2.30
    project
    2.14
     project
    1.94
     Projects
    1.90
     projects
    1.75
    projects
    1.74
     PRO
    1.40
     projector
    1.25
    PRO
    1.24
    Activations Density 2.635%

    No Known Activations