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. 17686
    Prev
    Next
    INDEX
    Explanations

    words related to qualities or states of being that are unchangeable or unwavering

    oai_token-act-pair · gpt-3.5-turbo

    phrases that signify the concept of "independence."

    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
    Ĥİ
    -0.79
     Lumpur
    -0.70
    BuyableInstoreAndOnline
    -0.67
    Gallery
    -0.61
    TION
    -0.58
     Later
    -0.56
     inference
    -0.54
     McGee
    -0.54
     drafts
    -0.54
    MQ
    -0.52
    POSITIVE LOGITS
    etermin
    1.26
    ignant
    1.11
    ented
    1.04
    irection
    0.99
    ivid
    0.99
    ocument
    0.93
    igent
    0.92
    orable
    0.91
    ol
    0.90
    esc
    0.89
    Activations Density 0.012%

    No Known Activations