© 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. 9-RES-JB
    11. 11192
    Prev
    Next
    INDEX
    Explanations

    phrases related to experiences and accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to enjoyment and significant life experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ults
    -0.72
    olitics
    -0.72
    vae
    -0.69
    state
    -0.67
    geist
    -0.66
    izes
    -0.65
    ENCE
    -0.65
    ucer
    -0.65
    cedes
    -0.64
    Gi
    -0.64
    POSITIVE LOGITS
     navigating
    1.65
     figuring
    1.54
     photograp
    1.50
     designing
    1.50
     organising
    1.47
     extracting
    1.46
     constructing
    1.43
     owning
    1.40
     discovering
    1.39
     assembling
    1.39
    Activations Density 0.794%

    No Known Activations