Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2066
    Prev
    Next
    INDEX
    Explanations

    comparative phrases using the word "as"

    oai_token-act-pair · gpt-3.5-turbo

    phrases and comparisons involving the word "as."

    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
    onomy
    -0.68
    OSE
    -0.68
    Ö¼
    -0.67
    YD
    -0.65
    âĹ¼
    -0.62
    ãģ®å®
    -0.62
    TAIN
    -0.62
    å½
    -0.61
    Nob
    -0.60
    ãĤ¤ãĥĪ
    -0.60
    POSITIVE LOGITS
     opposed
    0.99
    bestos
    0.98
    pects
    0.94
    pired
    0.90
    lihood
    0.89
    pires
    0.88
     well
    0.88
    ylum
    0.87
    criptions
    0.87
     regards
    0.84
    Activations Density 0.211%

    No Known Activations