© 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. 8-RES_POST_32K-OAI
    11. 7043
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations or groups associated with stem cell research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    743
    +0.11
    0.5%
    744
    +0.11
    0.5%
    11
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.03
    388
    +0.11
    0.04
    659
    +0.09
    0.03
    Negative Logits
    butt
    -0.82
    ishers
    -0.81
    tackle
    -0.80
    erers
    -0.77
    ries
    -0.76
    ished
    -0.76
    ishly
    -0.74
    shaw
    -0.72
    swer
    -0.72
    swick
    -0.71
    POSITIVE LOGITS
    ettings
    1.34
    ullivan
    1.18
    ync
    1.17
    ocial
    1.11
    aunders
    1.06
    ystem
    1.05
    essions
    1.03
    ELF
    1.01
    ESSION
    1.00
    ource
    1.00
    Activations Density 0.136%

    No Known Activations