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. 0-RES-JB
    6. 24445
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a consequence or outcome of events

    oai_token-act-pair · gpt-3.5-turbo

    instances of outcomes or consequences related to events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     talk
    -0.62
     nods
    -0.56
    ze
    -0.56
     Intro
    -0.55
     hawk
    -0.54
    nam
    -0.54
    ne
    -0.53
     Travels
    -0.52
    pheus
    -0.51
    Chat
    -0.51
    POSITIVE LOGITS
     resulted
    3.19
     culminated
    2.14
     ensued
    2.09
     yielded
    1.92
     occurred
    1.86
    result
    1.77
     consisted
    1.65
     coincided
    1.61
     lasted
    1.61
     amounted
    1.59
    Activations Density 0.013%

    No Known Activations