INDEX

Explanations

phrases relating to requirements and enhancements across various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 möjligt

-0.56

 Delight

-0.49

 possibilities

-0.48

useful

-0.48

 useful

-0.47

 proudly

-0.47

 helpful

-0.47

 utile

-0.47

 purported

-0.47

 possible

-0.46

POSITIVE LOGITS

才行

1.09

 careful

0.81

 somehow

0.78

 necessariamente

0.77

才能

0.75

 حتما

0.75

 necesariamente

0.70

 Somehow

0.67

が必要です

0.66

 carefully

0.64

Activations Density 0.827%

phrases relating to requirements and enhancements across various contexts

No Comments

No Known Activations