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. 18043
    Prev
    Next
    INDEX
    Explanations

    sports-related hashtags and social media handles

    oai_token-act-pair · gpt-3.5-turbo

    hashtags related to sports and social issues

    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
     substitute
    -0.83
     outset
    -0.72
     Levant
    -0.70
     assurance
    -0.70
     warranties
    -0.69
     Brill
    -0.69
     partner
    -0.67
     reins
    -0.67
     uncertain
    -0.67
     Schiff
    -0.66
    POSITIVE LOGITS
    _
    1.18
    __
    1.16
    2020
    1.14
    _.
    1.10
    Leaks
    1.04
    2016
    1.03
    Fail
    1.02
    pic
    1.00
    agate
    0.99
    2015
    0.99
    Activations Density 0.095%

    No Known Activations