© 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. 4589
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly those with the name "Ben" or similar derivatives

    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
    430
    +0.10
    0.5%
    497
    +0.10
    0.4%
    192
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.10
    0.04
    373
    +0.10
    -0.01
    232
    +0.08
    0.03
    Negative Logits
    oslav
    -0.66
    hett
    -0.59
     ratt
    -0.57
    rw
    -0.57
     insured
    -0.57
     Magnum
    -0.55
     Nex
    -0.54
     rotated
    -0.53
    ELF
    -0.53
    cube
    -0.53
    POSITIVE LOGITS
    amina
    0.82
    heid
    0.74
    atari
    0.71
    gui
    0.69
    etheus
    0.68
    iste
    0.68
    hovah
    0.65
    ×ķ
    0.65
    olicy
    0.63
    icio
    0.62
    Activations Density 0.149%

    No Known Activations