© 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 EvalsExportsinterp-engineNEWAPI 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. 27796
    Prev
    Next
    INDEX
    Explanations

    phrases conveying hope and compassion within a community context

    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
    756
    +0.13
    0.6%
    303
    +0.11
    0.5%
    759
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.13
    0.17
    759
    +0.11
    0.10
    7
    +0.11
    0.10
    Negative Logits
     dummy
    -0.88
     spam
    -0.85
     scams
    -0.81
     libel
    -0.80
     extortion
    -0.80
     Illegal
    -0.79
    gery
    -0.79
     ransomware
    -0.78
     disadvantages
    -0.77
     DMCA
    -0.76
    POSITIVE LOGITS
     awakening
    1.12
     reconnect
    1.10
     transformative
    1.09
     joyful
    1.07
     communion
    1.07
     transcend
    1.04
     upl
    1.03
     joy
    1.03
    nect
    1.02
     rebirth
    1.02
    Activations Density 5.244%

    No Known Activations