© 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. 8-RES-JB
    11. 2089
    Prev
    Next
    INDEX
    Explanations

    sentences in a conversational tone with punctuations at the end

    oai_token-act-pair · gpt-3.5-turbo

    instances of quoted dialogue or speech in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.66
     casualty
    -0.63
     Midnight
    -0.63
     obsess
    -0.60
     centrally
    -0.58
     grav
    -0.58
     sacrificed
    -0.58
     endeav
    -0.58
     graveyard
    -0.58
     inclusion
    -0.57
    POSITIVE LOGITS
    Correct
    1.06
    Lear
    0.96
    Tex
    0.89
    Bus
    0.88
    ONSORED
    0.88
    Asked
    0.87
    Write
    0.85
    He
    0.84
    METHOD
    0.83
    IRO
    0.82
    Activations Density 0.377%

    No Known Activations