Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 15956
    Prev
    Next
    INDEX
    Explanations

    elements related to online interaction and calls to action

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to streaming or online content engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     revers
    -0.83
     dece
    -0.78
     equival
    -0.77
     escaping
    -0.77
     actu
    -0.75
     eroded
    -0.75
     fleeing
    -0.74
     elim
    -0.73
     evapor
    -0.73
     reversing
    -0.72
    POSITIVE LOGITS
    Advertisements
    1.16
    =-=-=-=-=-=-=-=-
    1.13
    --------------------------------------------------------
    1.10
    Thank
    1.08
    Thanks
    1.04
    ################################
    1.02
    Feel
    1.01
    Lastly
    1.01
    Want
    1.00
    Congratulations
    1.00
    Activations Density 0.529%

    No Known Activations