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. 6-RES-JB
    6. 2322
    Prev
    Next
    INDEX
    Explanations

    dates or specific points in time mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    repetitive references to "this" and "that" in the context of specific topics or occasions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    upon
    -0.76
    letes
    -0.70
    ocate
    -0.69
    encers
    -0.69
    atron
    -0.68
    ãĥ©ãĥ³
    -0.68
    ults
    -0.65
    RIC
    -0.64
    inals
    -0.63
    LER
    -0.61
    POSITIVE LOGITS
     occasions
    1.53
     occasion
    1.35
     behalf
    1.25
     basis
    1.14
     shores
    0.99
     fronts
    0.98
     doorstep
    0.96
     occas
    0.94
    ilts
    0.93
     pretext
    0.93
    Activations Density 0.117%

    No Known Activations