INDEX

Explanations

measurements related to volume or quantity, specifically in cooking contexts

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

tsp or rtsp prefixes

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 Bowen

-0.52

 للاسماء

-0.47

umab

-0.44

WEBPACK

-0.44

berg

-0.44

julie

-0.43

각주

-0.42

 Riggs

-0.42

 otomatig

-0.42

 Barker

-0.41

POSITIVE LOGITS

tsp

2.19

 teaspoon

1.58

 teaspoons

1.42

tsp

1.27

 cucharadita

1.20

 cucchia

1.14

TSP

1.04

TSP

0.93

 tbsp

0.92

 cuchar

0.86

Activations Density 0.003%

measurements related to volume or quantity, specifically in cooking contexts

tsp or rtsp prefixes

No Comments

No Known Activations