© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 20192
    Prev
    Next
    INDEX
    Explanations

    terms related to blogging and bloggers

    oai_token-act-pair · gpt-3.5-turbo

    references to bloggers and blogging activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pesh
    -0.73
    inho
    -0.72
    atern
    -0.68
    IELD
    -0.68
     Centers
    -0.67
    xon
    -0.66
    LS
    -0.65
     Medicine
    -0.64
     Medic
    -0.64
    arching
    -0.62
    POSITIVE LOGITS
     blogger
    1.26
     blogging
    1.17
     bloggers
    1.16
    osphere
    1.05
    blogs
    0.97
    irtual
    0.96
    blogspot
    0.89
    culosis
    0.88
     blogs
    0.87
    sonian
    0.84
    Activations Density 0.006%

    No Known Activations