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. 16152
    Prev
    Next
    INDEX
    Explanations

    greetings or specific actions/events with a high emotional impact

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various roles and conditions within complex scenarios

    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
     channels
    -0.61
     Klux
    -0.58
     Machines
    -0.57
     Sections
    -0.56
     Scouts
    -0.56
     Clubs
    -0.53
    renches
    -0.52
    apeake
    -0.52
     offices
    -0.51
     Traps
    -0.51
    POSITIVE LOGITS
     consisting
    0.79
     standpoint
    0.73
    cko
    0.67
     comprised
    0.63
    ifier
    0.63
     akin
    0.62
     resembling
    0.60
     costing
    0.59
     involving
    0.58
     meant
    0.57
    Activations Density 0.702%

    No Known Activations