INDEX

Explanations

elements of structured programming or data entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

RTLD

-0.53

leski

-0.53

LabelTagHelper

-0.52

 Polsek

-0.51

تقاوى

-0.49

Itoa

-0.49

 للمعارف

-0.49

kons

-0.49

LOOKUP

-0.47

 ModelExpression

-0.47

POSITIVE LOGITS

 purpoſe

0.86

ChildScrollView

0.81

 myſelf

0.79

 pleaſure

0.75

 perſon

0.73

 uſed

0.72

 ſtate

0.71

 ſeveral

0.69

TargetException

0.69

Efq

0.69

Activations Density 0.172%

elements of structured programming or data entities

No Comments

No Known Activations

elements of structured programming or data entities

No Comments

No Known Activations