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. 1-RES-JB
    6. 18232
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences beginning with the word "as"

    oai_token-act-pair · gpt-3.5-turbo

    the word "as" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.65
    Gear
    -0.62
    oller
    -0.61
    Enlarge
    -0.59
    OUR
    -0.58
    bryce
    -0.58
    âĹ¼
    -0.57
    Reply
    -0.55
    YD
    -0.55
    TPS
    -0.54
    POSITIVE LOGITS
    bestos
    1.07
    pired
    1.05
    pires
    0.92
    phalt
    0.89
     well
    0.87
    phy
    0.87
     evidenced
    0.86
     opposed
    0.86
    ynchron
    0.86
    criptions
    0.85
    Activations Density 0.283%

    No Known Activations