© 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. 3546
    Prev
    Next
    INDEX
    Explanations

    words signaling comparison or potential actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of lists or enumerations

    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
    ety
    -0.78
    iple
    -0.69
    cember
    -0.65
    herent
    -0.62
    lore
    -0.61
    uscript
    -0.59
    usra
    -0.59
    lord
    -0.59
    vre
    -0.58
     nutshell
    -0.58
    POSITIVE LOGITS
     regardless
    1.21
     lest
    1.19
     preferably
    1.18
     irrespective
    1.08
     thereby
    1.04
     albeit
    1.03
     however
    0.98
     whereas
    0.93
     unless
    0.93
     depending
    0.93
    Activations Density 0.584%

    No Known Activations