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. 2-RES-JB
    6. 157
    Prev
    Next
    INDEX
    Explanations

    the root "rad" in different contexts

    oai_token-act-pair · gpt-4-turbo

    words related to radiation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to radiation and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    batch
    -0.77
    OOL
    -0.70
    stall
    -0.69
    ãĥīãĥ©
    -0.67
    eers
    -0.66
     Rowling
    -0.66
    Reloaded
    -0.65
    FAULT
    -0.65
     Hundred
    -0.64
    BOOK
    -0.63
    POSITIVE LOGITS
    iated
    1.20
     rad
    1.15
    iance
    1.12
    iation
    1.03
    iations
    0.99
    iating
    0.97
    ient
    0.93
    irtual
    0.91
    iate
    0.90
    ionics
    0.90
    Activations Density 0.006%

    No Known Activations