© 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. 29639
    Prev
    Next
    INDEX
    Explanations

    concepts related to academic freedom and freedom of speech

    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
    411
    +0.10
    0.4%
    103
    +0.10
    0.4%
    499
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.10
    0.05
    680
    +0.10
    0.03
    608
    +0.10
    0.15
    Negative Logits
     Predators
    -0.78
    ustom
    -0.75
     GoPro
    -0.74
     Predator
    -0.72
    oshenko
    -0.72
     corrid
    -0.72
     fisherman
    -0.71
     Daredevil
    -0.70
     WATCHED
    -0.70
     glim
    -0.70
    POSITIVE LOGITS
     campus
    2.15
     faculty
    2.11
     professors
    2.05
     campuses
    1.98
     tuition
    1.97
    campus
    1.97
     undergrad
    1.95
     university
    1.95
     Faculty
    1.94
     semester
    1.89
    Activations Density 8.305%

    No Known Activations