© 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. 32399
    Prev
    Next
    INDEX
    Explanations

    references to biodiversity and threatened species

    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
    425
    +0.10
    0.4%
    725
    +0.10
    0.4%
    17
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.10
    0.08
    1
    +0.10
    0.06
    27
    +0.09
    0.06
    Negative Logits
    ruary
    -0.85
    pee
    -0.80
    soDeliveryDate
    -0.80
    poon
    -0.78
    DCS
    -0.72
    äºĶ
    -0.72
    essage
    -0.71
    çĶ°
    -0.71
    Pope
    -0.71
    zsche
    -0.71
    POSITIVE LOGITS
     organisms
    1.52
     animals
    1.45
     creatures
    1.45
     mammals
    1.28
     insects
    1.27
     species
    1.27
     wildlife
    1.21
     beasts
    1.21
    organisms
    1.19
     pests
    1.19
    Activations Density 1.563%

    No Known Activations