INDEX

Explanations

instances of software-related terms and legal jargon

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

no

-0.59

“

-0.52

↵↵

-0.48

↵

-0.47

-0.46

non

-0.45

on

-0.44

无

-0.43

$\

-0.43

POSITIVE LOGITS

+#+#

1.28

álja

1.07

MemoryWarning

1.01

'{@

0.99

 AttributeSet

0.98

ChildScrollView

0.98

RectangleBorder

0.97

PerformLayout

0.94

 propOrder

0.93

 مرئيه

0.92

Activations Density 0.308%

instances of software-related terms and legal jargon

No Comments

No Known Activations