Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 6-RES_POST_32K-OAI
    6. 4219
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Juan"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_6.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    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
    515
    +0.12
    0.5%
    31
    +0.11
    0.5%
    267
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.01
    511
    +0.11
    0.01
    515
    +0.11
    0.01
    Negative Logits
    ENDED
    -0.73
     subp
    -0.69
    ramid
    -0.68
    ħĭ
    -0.67
    displayText
    -0.66
     guiActiveUn
    -0.63
    Ö¼
    -0.63
     javascript
    -0.62
     Xeon
    -0.62
     Revelations
    -0.61
    POSITIVE LOGITS
    ities
    0.90
    assis
    0.88
    ciating
    0.86
    ITY
    0.86
    idad
    0.85
    icious
    0.82
    ette
    0.81
    igans
    0.80
    iverse
    0.79
    aval
    0.78
    Activations Density 0.043%

    No Known Activations