© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 12446
    Prev
    Next
    INDEX
    Explanations

    phrases related to educational institutions and activities

    oai_token-act-pair · gpt-3.5-turbo

    quantitative information related to education systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VPN
    -0.80
    gency
    -0.77
    FX
    -0.73
     Cheong
    -0.70
    cation
    -0.68
    soType
    -0.67
    NetMessage
    -0.67
    imposed
    -0.67
     creditor
    -0.67
    Offline
    -0.67
    POSITIVE LOGITS
     youngsters
    1.87
     kids
    1.69
     youths
    1.64
     students
    1.60
     teenagers
    1.60
     pupils
    1.59
     children
    1.59
     adolescents
    1.56
     young
    1.54
     freshmen
    1.52
    Activations Density 0.355%

    No Known Activations