© 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
    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. 20451
    Prev
    Next
    INDEX
    Explanations

    phrases related to progress on projects and tasks

    oai_token-act-pair · gpt-3.5-turbo

    details related to project management and progress

    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
     Phelps
    -0.84
     Hannity
    -0.78
     pharmacies
    -0.76
     Limbaugh
    -0.76
     Santorum
    -0.75
     Humph
    -0.74
    chens
    -0.73
    olitics
    -0.73
    Conservative
    -0.73
     Eaton
    -0.72
    POSITIVE LOGITS
     prototypes
    1.61
     prototype
    1.51
     Prototype
    1.38
     sketches
    1.35
     development
    1.34
     prototyp
    1.33
     SDK
    1.25
     project
    1.22
    Development
    1.22
     revisions
    1.20
    Activations Density 0.661%

    No Known Activations