© 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. 10-RES_POST_32K-OAI
    6. 29699
    Prev
    Next
    INDEX
    Explanations

    topics related to political and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    +0.12
    0.5%
    355
    +0.11
    0.5%
    127
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.12
    0.13
    439
    +0.11
    0.10
    288
    +0.10
    0.13
    Negative Logits
    anwhile
    -0.83
    etheless
    -0.73
    ierrez
    -0.71
    !:
    -0.71
     reportedly
    -0.69
     wondered
    -0.68
    +.
    -0.67
     meanwhile
    -0.67
    :]
    -0.65
     speculated
    -0.65
    POSITIVE LOGITS
     unfairly
    1.09
     outweigh
    0.99
     justifies
    0.95
     infring
    0.92
     constitutes
    0.85
     violates
    0.83
     adequately
    0.82
     constituted
    0.81
     accurately
    0.80
     unconstitutional
    0.79
    Activations Density 1.463%

    No Known Activations