INDEX

Explanations

references to legal terminology and concepts related to court proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

而

-0.52

。

-0.48

而

-0.48

 tandis

-0.43

↵↵

-0.43

↵

-0.43

UTE

-0.42

<blockquote>

-0.42

硫

-0.41

sə

-0.40

POSITIVE LOGITS

 will

1.08

 would

1.05

is

1.03

has

1.01

Datuak

0.98

can

0.96

 could

0.95

had

0.95

was

0.93

 linkovi

0.86

Activations Density 2.216%

references to legal terminology and concepts related to court proceedings

No Comments

No Known Activations