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. 22998
    Prev
    Next
    INDEX
    Explanations

    words related to physical sensations or reactions, especially when repeated for emphasis

    oai_token-act-pair · gpt-3.5-turbo

    the word "sp" and its variations, indicating a focus on terms related to playful or casual contexts

    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
    */(
    -0.78
    heit
    -0.78
    DragonMagazine
    -0.78
    obyl
    -0.78
     Incarnation
    -0.76
     approve
    -0.69
    ergy
    -0.67
    ablishment
    -0.66
     Masters
    -0.65
    ezvous
    -0.65
    POSITIVE LOGITS
    amm
    0.89
    acer
    0.89
    anky
    0.88
    rocket
    0.86
    itt
    0.85
    ank
    0.85
    atial
    0.84
    inn
    0.84
    orp
    0.83
    ooky
    0.82
    Activations Density 0.011%

    No Known Activations