INDEX

Explanations

references to prompts or signals that indicate behavior or responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

__((

-0.71

 disambiguazione

-0.66

srcs

-0.65

mente

-0.62

ه

-0.60

ات

-0.59

rektur

-0.58

 nakalista

-0.58

WEBPACK

-0.57

antz

-0.57

POSITIVE LOGITS

iness

0.72

 ویکی‌پدیای

0.70

 NDEBUG

0.60

бище

0.60

StructEnd

0.59

 متحده

0.57

SerializedSize

0.57

первых

0.56

NameInMap

0.55

ؤلاء

0.55

Activations Density 0.858%

references to prompts or signals that indicate behavior or responses

No Comments

No Known Activations