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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9228
    Prev
    Next
    INDEX
    Explanations

    phrases related to preparing for future events or occasions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and its related phrases indicating preparation for events

    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
     interacted
    -0.74
     countered
    -0.72
     liked
    -0.71
    cloth
    -0.71
     existed
    -0.70
     Played
    -0.69
    etsy
    -0.68
     insofar
    -0.68
    ourced
    -0.68
     distinguishes
    -0.68
    POSITIVE LOGITS
     inevitable
    1.26
     unveiling
    1.21
     arrival
    1.19
     impending
    1.16
     onset
    1.15
     final
    1.15
     upcoming
    1.11
     remainder
    1.10
     initiation
    1.06
     eventual
    1.04
    Activations Density 0.315%

    No Known Activations