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. 8-RES-JB
    6. 20562
    Prev
    Next
    INDEX
    Explanations

    uncommon special characters, especially those that attempt to represent specific emotions or actions

    oai_token-act-pair · gpt-3.5-turbo

    moments of suspense or tension in the narrative

    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
     fres
    -0.75
     critics
    -0.73
     allege
    -0.72
     appoint
    -0.71
     moder
    -0.69
     representation
    -0.69
     alleged
    -0.69
     confir
    -0.69
     billed
    -0.68
     championed
    -0.68
    POSITIVE LOGITS
    Suddenly
    1.30
    ::::::::
    1.21
    Chapter
    1.18
    CHAPTER
    1.08
    ************
    1.05
    XXXX
    1.04
    âĶĢâĶĢ
    1.02
    Seeing
    1.02
    rawdownloadcloneembedreportprint
    1.00
    Elsa
    0.99
    Activations Density 0.190%

    No Known Activations