© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 29132
    Prev
    Next
    INDEX
    Explanations

    expressions of hope and potential for future success

    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
    86
    +0.11
    0.5%
    459
    +0.11
    0.5%
    690
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.11
    0.15
    665
    +0.11
    0.16
    86
    +0.10
    0.13
    Negative Logits
     censored
    -0.95
     Stupid
    -0.87
     disapprove
    -0.85
     cheating
    -0.82
     forbids
    -0.81
     illiter
    -0.78
    racist
    -0.78
     disapproval
    -0.78
     inacc
    -0.78
     disgust
    -0.77
    POSITIVE LOGITS
     cement
    1.02
     rejuven
    0.96
    ocused
    0.94
     embark
    0.93
     broaden
    0.91
     consolidate
    0.90
     regain
    0.89
     establish
    0.89
     showcase
    0.89
     solid
    0.88
    Activations Density 2.202%

    No Known Activations