INDEX

Explanations

phrases emphasizing the word "that" in various contexts

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

NameInMap

-0.91

 pleaſure

-0.84

 viſ

-0.79

eſt

-0.75

 myſelf

-0.74

 ſever

-0.74

 Conſ

-0.71

 Majefty

-0.71

VIC

-0.70

 Reſ

-0.70

POSITIVE LOGITS

 that

2.83

that

2.21

 bahwa

1.86

 That

1.68

 bahawa

1.64

 THAT

1.62

That

1.61

THAT

1.56

 ότι

1.44

że

1.36

Activations Density 0.545%

phrases emphasizing the word "that" in various contexts

No Comments

No Known Activations