INDEX

Explanations

phrases related to significant historical events or disasters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 /\.(

-0.68

RegressionTest

-0.67

########.

-0.61

tempuran

-0.60

('/:

-0.59

ἶ

-0.58

__(/*!

-0.58

("\"

-0.57

glfw

-0.56

 stanov

-0.55

POSITIVE LOGITS

ValueStyle

0.80

SequentialGroup

0.77

 BorderRadius

0.67

 nonatomic

0.66

 Inflate

0.65

BeginInit

0.64

NegativeButton

0.61

picasso

0.59

addPreferredGap

0.59

 atque

0.59

Activations Density 0.011%

phrases related to significant historical events or disasters

No Comments

No Known Activations