Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 3998
    Prev
    Next
    INDEX
    Explanations

    mentions of projects or developments that are currently in progress or available

    oai_token-act-pair · gpt-3.5-turbo

    the word "currently" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bold
    -0.74
    vg
    -0.73
     Geh
    -0.73
    later
    -0.71
    once
    -0.69
    vation
    -0.68
    alty
    -0.67
    jl
    -0.67
    step
    -0.67
    Secondly
    -0.65
    POSITIVE LOGITS
     residing
    1.03
     underway
    1.01
     undergoing
    0.94
     awaiting
    0.91
     unavailable
    0.88
     langu
    0.85
     undecided
    0.85
     resides
    0.84
     enrolled
    0.83
     embroiled
    0.82
    Activations Density 0.045%

    No Known Activations