INDEX

Explanations

references to numerical values or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

<eos>

-0.47

-0.45

↵↵

-0.45

Ver

-0.44

-0.43

-0.42

era

-0.42

ong

-0.42

ned

-0.42

vý

-0.41

POSITIVE LOGITS

 ویکی‌پدیا

1.06

]<<"

0.96

 Normdatei

0.96

AndEndTag

0.94

IonicModule

0.92

CodedInputStream

0.90

 TextAppearance

0.88

OGND

0.86

+#+#

0.86

 HttpHeaders

0.86

Activations Density 0.795%

references to numerical values or statistics

No Comments

No Known Activations