© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 5579
    Prev
    Next
    INDEX
    Explanations

    numerical data and values

    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
    373
    +0.17
    0.8%
    504
    +0.10
    0.5%
    599
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.17
    0.04
    316
    +0.10
    0.04
    284
    +0.10
    0.03
    Negative Logits
    ailed
    -0.65
    sie
    -0.65
    tails
    -0.64
    ket
    -0.63
     kits
    -0.61
     graduates
    -0.60
    manship
    -0.59
     graffiti
    -0.59
    sing
    -0.59
    -+-+-+-+
    -0.59
    POSITIVE LOGITS
    ,-
    0.78
    emet
    0.73
    yards
    0.68
    ]=
    0.66
    WARD
    0.66
    Zone
    0.65
     URL
    0.65
    "]=>
    0.64
     Zone
    0.64
     partName
    0.62
    Activations Density 0.153%

    No Known Activations