© 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. 6-RES-JB
    11. 13718
    Prev
    Next
    INDEX
    Explanations

    texts denoted by Ċ that introduce a new section or paragraph

    oai_token-act-pair · gpt-3.5-turbo

    structured discussions about various topics or issues

    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
     disapprove
    -0.67
    boro
    -0.67
     equip
    -0.64
     manoeuv
    -0.64
     withdraw
    -0.63
    undle
    -0.62
    utical
    -0.62
    utic
    -0.61
     inactive
    -0.61
     Vald
    -0.61
    POSITIVE LOGITS
    ³³³
    1.07
    ³³³³
    1.06
    ³³³³³³³³³³³³³³³³
    0.99
    ³³³³³³³³
    0.91
    ³³
    0.88
    Consider
    0.84
    Firstly
    0.81
    Reason
    0.81
    Anyway
    0.81
    Specifically
    0.80
    Activations Density 0.675%

    No Known Activations