INDEX

Explanations

multiple instances of the same tokens or related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

TintMode

-0.60

 по

-0.49

-0.48

 serca

-0.45

 Приступљено

-0.43

HomeAsUpEnabled

-0.43

 internacionais

-0.42

TargetException

-0.42

↵↵

-0.41

Mutagenicity

-0.41

POSITIVE LOGITS

ſelves

0.85

ſelf

0.85

Jîn

0.84

 tartalomajánló

0.80

moiselle

0.79

 للمعارف

0.77

 ſtate

0.76

neſs

0.75

 Majefty

0.73

 eſt

0.72

Activations Density 0.356%

multiple instances of the same tokens or related terms

No Comments

No Known Activations