© 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. 17382
    Prev
    Next
    INDEX
    Explanations

    the word "newly" followed by various scenarios or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "newly" and its variations

    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
    rice
    -0.78
    ancial
    -0.77
    ospace
    -0.75
    ocene
    -0.75
    retty
    -0.74
    ĺħ
    -0.74
    igraph
    -0.74
    orem
    -0.71
    otaur
    -0.70
     Bastard
    -0.69
    POSITIVE LOGITS
    wed
    0.94
     appointed
    0.93
     liberated
    0.85
     acquired
    0.84
    bie
    0.83
    ãĤ»
    0.81
     awakened
    0.81
     planted
    0.80
     crowned
    0.79
     mint
    0.79
    Activations Density 0.019%

    No Known Activations