© 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. 4706
    Prev
    Next
    INDEX
    Explanations

    words related to clothing and costumes

    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
    595
    +0.10
    0.5%
    373
    +0.10
    0.5%
    241
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.12
    326
    +0.10
    0.10
    575
    +0.10
    0.10
    Negative Logits
    £ı
    -0.72
     Kazakh
    -0.67
    rians
    -0.66
    auri
    -0.66
     Kern
    -0.65
     valleys
    -0.64
    esm
    -0.64
    izons
    -0.63
    erate
    -0.62
    ional
    -0.61
    POSITIVE LOGITS
     holder
    1.00
     worn
    1.00
     wearer
    0.99
     adorned
    0.95
     strapped
    0.89
     manufacturer
    0.88
     equipped
    0.88
     sleeve
    0.87
     containing
    0.87
     salesman
    0.87
    Activations Density 1.175%

    No Known Activations