© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5595
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations and associated cultural identities

    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
    725
    +0.11
    0.5%
    373
    +0.10
    0.5%
    546
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.07
    612
    +0.10
    0.06
    103
    +0.10
    0.05
    Negative Logits
    geist
    -0.77
    agonist
    -0.75
    Reviewer
    -0.73
    metal
    -0.71
     Catalyst
    -0.68
    Tube
    -0.67
    Glass
    -0.67
    xus
    -0.67
    \/\/
    -0.66
    Apps
    -0.66
    POSITIVE LOGITS
     Islands
    1.09
     Guam
    0.98
     islands
    0.91
     Monteneg
    0.89
     Albania
    0.85
     Guatemala
    0.85
     Caribbean
    0.85
     Bermuda
    0.84
    cair
    0.84
     Kosovo
    0.83
    Activations Density 0.476%

    No Known Activations