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. 0-RES-JB
    6. 17378
    Prev
    Next
    INDEX
    Explanations

    references to remote or remote-controlled activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "remotely."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fill
    -0.63
    ieu
    -0.62
     Pieces
    -0.60
     Athletic
    -0.59
    pu
    -0.59
    amide
    -0.59
     Mant
    -0.58
    itol
    -0.57
    bt
    -0.57
     prev
    -0.57
    POSITIVE LOGITS
     remotely
    4.15
    remote
    1.61
    Remote
    1.46
     remote
    1.45
     Remote
    1.40
     electronically
    1.17
     vaguely
    1.13
     digitally
    1.11
     centrally
    1.01
     dynamically
    0.99
    Activations Density 0.017%

    No Known Activations