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. 6-RES-JB
    6. 24045
    Prev
    Next
    INDEX
    Explanations

    personal pronouns indicating family members and relationships

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and references to groups or relationships among people

    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
    earch
    -0.72
    cade
    -0.71
    tained
    -0.67
    CAP
    -0.67
    UTC
    -0.67
    ienne
    -0.65
    tains
    -0.64
    oward
    -0.62
     pressing
    -0.61
    DAY
    -0.60
    POSITIVE LOGITS
    'll
    1.06
    're
    1.02
    've
    0.97
     ain
    0.89
    reditary
    0.87
    selves
    0.87
    self
    0.77
     goddamn
    0.77
     can
    0.76
     gotta
    0.76
    Activations Density 0.352%

    No Known Activations