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. 10656
    Prev
    Next
    INDEX
    Explanations

    phrases related to the topic or subject matter being discussed

    oai_token-act-pair · gpt-3.5-turbo

    references to the topic of discussion or general conversational context

    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
     lines
    -0.67
     line
    -0.65
     primaries
    -0.64
     states
    -0.61
     cons
    -0.60
     sat
    -0.59
     Line
    -0.59
     Province
    -0.58
     saturation
    -0.58
     Tier
    -0.57
    POSITIVE LOGITS
    about
    4.16
    abouts
    2.93
    around
    1.83
    About
    1.77
     ABOUT
    1.75
     About
    1.71
    approximately
    1.30
     about
    1.30
    enough
    1.16
    between
    1.03
    Activations Density 0.015%

    No Known Activations