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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 4207
    Prev
    Next
    INDEX
    Explanations

    references to physical structures and their characteristics

    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
    36
    +0.12
    0.5%
    71
    +0.11
    0.5%
    441
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    264
    +0.12
    0.01
    288
    +0.11
    0.02
    516
    +0.10
    0.01
    Negative Logits
    20439
    -0.79
    rawdownloadcloneembedreportprint
    -0.79
    taboola
    -0.78
    ãĥ¼ãĥĨ
    -0.76
    âĹ¼
    -0.76
    ãĥķãĤ¡
    -0.72
    bourg
    -0.70
    DragonMagazine
    -0.69
    abl
    -0.69
    Sensor
    -0.68
    POSITIVE LOGITS
    ignt
    0.72
    folios
    0.69
     portrait
    0.68
     exha
    0.66
    eatures
    0.63
     resting
    0.62
     seiz
    0.62
     dexter
    0.62
     grave
    0.61
     eagle
    0.61
    Activations Density 0.080%

    No Known Activations