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. 19496
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Silk Road."

    oai_token-act-pair · gpt-3.5-turbo

    references to the online marketplace "Silk Road."

    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
    DEP
    -0.77
    ner
    -0.67
     ref
    -0.66
     comp
    -0.64
     qualified
    -0.63
    ré
    -0.63
     alleg
    -0.63
    ATED
    -0.63
     refere
    -0.63
     recall
    -0.62
    POSITIVE LOGITS
     Silk
    4.30
     silk
    2.13
    Sil
    1.56
    sil
    1.24
     Cotton
    1.21
     Velvet
    1.16
     Spice
    1.15
     Hemp
    1.13
     DPR
    1.11
     Sina
    1.10
    Activations Density 0.030%

    No Known Activations