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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7353
    Prev
    Next
    INDEX
    Explanations

    the name "Bach" appearing in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Bach."

    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
     line
    -0.65
     Nim
    -0.64
     way
    -0.63
     Terr
    -0.62
     malicious
    -0.62
     straight
    -0.61
     torch
    -0.61
     Ku
    -0.60
     Ru
    -0.60
     enemy
    -0.60
    POSITIVE LOGITS
    bach
    4.81
    baugh
    2.07
    baum
    1.48
    meier
    1.46
    beck
    1.44
    stadt
    1.41
    berger
    1.41
    furt
    1.37
    witz
    1.34
    kamp
    1.32
    Activations Density 0.011%

    No Known Activations