© 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. 10-RES-JB
    11. 20617
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussions or points of interest in a formal context

    oai_token-act-pair · gpt-3.5-turbo

    topics related to political or social issues under discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imitation
    -0.76
     imitate
    -0.67
     footprints
    -0.67
     dup
    -0.66
     warranties
    -0.64
    oop
    -0.64
    robe
    -0.63
    SON
    -0.63
     Estimated
    -0.62
    ramids
    -0.62
    POSITIVE LOGITS
     debated
    1.34
     unresolved
    1.18
     contentious
    1.13
     debates
    1.08
     hotly
    1.08
     debate
    1.05
    Issue
    1.05
    issues
    1.04
     divisive
    1.01
     topic
    1.00
    Activations Density 0.324%

    No Known Activations