INDEX

Explanations

phrases indicating a breadth of selection or diversity in options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

ècie

-0.72

QMetaType

-0.72

JNIEnv

-0.68

ReusableCell

-0.68

 ModelExpression

-0.65

WidgetItem

-0.64

Sucesor

-0.64

MessageOf

-0.63

yntaxException

-0.62

PRNewswire

-0.61

POSITIVE LOGITS

 range

1.03

 WIDE

0.95

 wide

0.94

 Wide

0.92

WIDE

0.89

Wide

0.86

 ranging

0.82

 spectrum

0.81

 broad

0.81

 RANGE

0.80

Activations Density 0.108%

phrases indicating a breadth of selection or diversity in options

No Comments

No Known Activations