© 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. 6-RES-JB
    11. 17443
    Prev
    Next
    INDEX
    Explanations

    phrases ending in 'rebate'

    oai_token-act-pair · gpt-3.5-turbo

    non-verbal markers or symbols that indicate formatting or special characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pictured
    -0.72
     Io
    -0.72
     afar
    -0.72
     docks
    -0.69
     nearby
    -0.65
     monet
    -0.64
     Yad
    -0.64
     stomp
    -0.64
     armour
    -0.64
     inspecting
    -0.63
    POSITIVE LOGITS
    Disclaimer
    1.09
    Letter
    1.05
    Introduction
    1.04
    TABLE
    0.98
    Chapter
    0.95
    CHAPTER
    0.95
    PART
    0.95
    LET
    0.94
    Dear
    0.93
    GREEN
    0.89
    Activations Density 0.428%

    No Known Activations