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. 9-RES-JB
    6. 20967
    Prev
    Next
    INDEX
    Explanations

    keywords related to hashtags and events in social media

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sports events and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     substitute
    -0.84
     Forge
    -0.81
     Kuh
    -0.76
     Ples
    -0.76
     theoretical
    -0.75
     Brill
    -0.74
     attendant
    -0.74
     Equip
    -0.74
     mathemat
    -0.72
     counselor
    -0.71
    POSITIVE LOGITS
    2016
    1.33
    2017
    1.26
    2020
    1.26
    2015
    1.26
    2014
    1.24
    2012
    1.20
    pic
    1.18
    Fail
    1.17
    Days
    1.15
    2013
    1.14
    Activations Density 0.080%

    No Known Activations