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. 3-RES-JB
    6. 13978
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by a statement of certainty or commitment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "I" and variations of personal to indicate self-reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     buzz
    -0.65
    bard
    -0.64
     pitch
    -0.64
    krit
    -0.62
     giveaway
    -0.62
     foul
    -0.61
     Topic
    -0.58
     sidx
    -0.58
     Behavior
    -0.58
     nexus
    -0.57
    POSITIVE LOGITS
    ortal
    1.13
    umbai
    1.02
    ighty
    1.00
    ichael
    1.00
    igr
    0.96
    useum
    0.95
    igration
    0.92
    asonry
    0.91
    uppet
    0.91
    selves
    0.91
    Activations Density 0.044%

    No Known Activations