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. 2-RES-JB
    6. 4644
    Prev
    Next
    INDEX
    Explanations

    first-person singular statements indicating a personal stance or opinion

    oai_token-act-pair · gpt-3.5-turbo

    the word "I" and related personal pronouns or self-referential expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eleven
    -0.67
     Dangerous
    -0.66
     Levant
    -0.65
    EStream
    -0.64
     Topic
    -0.62
    irtual
    -0.61
    bard
    -0.61
     pitch
    -0.60
    DragonMagazine
    -0.60
     Behavior
    -0.58
    POSITIVE LOGITS
    ichael
    1.13
    igr
    1.11
    ortal
    1.11
    obil
    1.10
    useum
    1.08
    umbai
    1.08
    otor
    1.07
    asonry
    1.04
    igrants
    1.02
    ormon
    1.01
    Activations Density 0.060%

    No Known Activations