INDEX

Explanations

references to "plate" and "dishes."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

includegraphics

-0.59

udit

-0.54

 geblieben

-0.53

 iesp

-0.51

abancı

-0.51

 fenti

-0.51

 Mukherjee

-0.50

Modified

-0.50

참고

-0.49

 omge

-0.49

POSITIVE LOGITS

 plate

1.21

 plates

1.17

 Plates

1.13

 dish

1.11

plate

1.05

 Plate

1.03

plates

1.03

 PLATES

1.02

Plate

1.01

 PLATE

1.00

Activations Density 0.072%

references to "plate" and "dishes."

No Comments

No Known Activations