© 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. 13555
    Prev
    Next
    INDEX
    Explanations

    phrases related to persistence or continuing a current path or strategy

    oai_token-act-pair · gpt-3.5-turbo

    common phrases and terms associated with maintaining proximity or adherence to a course of action

    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
    catentry
    -0.88
    è¦ļéĨĴ
    -0.70
    elf
    -0.65
    çīĪ
    -0.63
    YR
    -0.62
     Eclipse
    -0.62
    ELL
    -0.62
     Macintosh
    -0.61
    wcsstore
    -0.60
    VIDIA
    -0.60
    POSITIVE LOGITS
     indefinitely
    0.90
    lishes
    0.88
     forever
    0.77
     bounds
    0.76
     haunt
    0.75
     afloat
    0.75
    andestine
    0.73
     limbo
    0.72
     steadfast
    0.72
     haun
    0.67
    Activations Density 0.098%

    No Known Activations