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. 11-RES-JB
    6. 10570
    Prev
    Next
    INDEX
    Explanations

    years or date ranges provided in the format of 'year1 - year2'

    oai_token-act-pair · gpt-3.5-turbo

    sequences of hyphenated numbers representing sports seasons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zoro
    -0.72
     Sparrow
    -0.67
     280
    -0.66
     310
    -0.65
     274
    -0.65
     Harmon
    -0.63
     sixty
    -0.63
     Mex
    -0.62
     fifty
    -0.62
     Afric
    -0.62
    POSITIVE LOGITS
    2017
    1.36
    2016
    1.36
    present
    1.35
    2020
    1.34
    2015
    1.31
    2018
    1.27
    2014
    1.26
    2019
    1.21
    2013
    1.21
    Present
    1.20
    Activations Density 0.031%

    No Known Activations