© 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. 0-RES-JB
    11. 11348
    Prev
    Next
    INDEX
    Explanations

    phrases related to injection procedures, specifically in medical or technical contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of injections, particularly in medical and technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Prev
    -0.78
     Vanessa
    -0.73
    deb
    -0.72
     Brill
    -0.72
     Discord
    -0.71
    friends
    -0.71
    Story
    -0.70
    pires
    -0.67
    stable
    -0.65
    arthed
    -0.65
    POSITIVE LOGITS
     injection
    3.90
     injections
    2.58
    jection
    1.78
     infusion
    1.69
     injecting
    1.26
     injected
    1.14
     induction
    1.07
     ingestion
    1.03
     insertion
    1.02
     overdose
    1.02
    Activations Density 0.012%

    No Known Activations