© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 6457
    Prev
    Next
    INDEX
    Explanations

    references to specific technical terms or acronyms like "GT" and "BP."

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms that are often related to organizations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mers
    -0.68
    fully
    -0.67
     Peninsula
    -0.67
     cal
    -0.66
     Vec
    -0.66
    brook
    -0.65
    ré
    -0.64
     disg
    -0.64
    c
    -0.63
     Context
    -0.62
    POSITIVE LOGITS
    okemon
    1.05
    ansion
    0.96
    urities
    0.95
    folios
    0.92
    ocalypse
    0.92
    ossibility
    0.91
    culosis
    0.91
    urity
    0.90
    roleum
    0.86
    ambers
    0.85
    Activations Density 0.015%

    No Known Activations