© 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. 29110
    Prev
    Next
    INDEX
    Explanations

    names and geographical references

    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
    662
    +0.11
    0.5%
    691
    +0.10
    0.5%
    41
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.08
    232
    +0.10
    0.07
    314
    +0.10
    0.01
    Negative Logits
     Franç
    -0.81
     Canad
    -0.74
     Skinner
    -0.70
     fixme
    -0.69
    bourg
    -0.67
     Vale
    -0.67
     Fasc
    -0.65
     apologies
    -0.65
     Fem
    -0.64
     Situation
    -0.64
    POSITIVE LOGITS
    hovah
    1.30
    ijah
    1.23
     Judah
    1.11
    Ö
    1.09
    Israel
    1.05
    Isa
    1.05
     Isaiah
    1.01
    veh
    1.01
    NAS
    1.01
     Jehovah
    1.00
    Activations Density 0.429%

    No Known Activations