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. 8-RES-JB
    6. 9237
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific entity or topic within a longer discussion context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itiz
    -0.77
    ional
    -0.72
    irds
    -0.68
    abe
    -0.64
    Topics
    -0.62
    pointers
    -0.62
     owes
    -0.62
    #$
    -0.62
     malf
    -0.61
    uty
    -0.61
    POSITIVE LOGITS
     meantime
    1.66
     midst
    1.37
     aftermath
    1.26
     absence
    1.23
     context
    1.07
     simplest
    1.05
     guise
    1.04
     ensuing
    1.01
     wake
    1.00
     meanwhile
    0.98
    Activations Density 0.167%

    No Known Activations