INDEX

Explanations

comparative phrases or constructs emphasizing similarity or equality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Sama

-0.60

Dla

-0.58

 Judah

-0.58

olu

-0.57

YourGuide

-0.57

","","

-0.56

 Jackson

-0.56

 Jacobs

-0.55

 Gloria

-0.55

いません

-0.54

POSITIVE LOGITS

principalTable

0.79

原始内容存档于

0.76

Tembelea

0.75

 possible

0.75

ashier

0.75

InjectAttribute

0.73

 EconPapers

0.72

 llamo

0.72

 Argyle

0.72

onAttach

0.71

Activations Density 0.074%

comparative phrases or constructs emphasizing similarity or equality

No Comments

No Known Activations