INDEX

Explanations

words related to academic investigations and discussions

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

 ویکی‌پدیای

-0.74

DebuggerNonUser

-0.72

 tartalomajánló

-0.67

ToBounds

-0.64

 NDEBUG

-0.63

 الحره

-0.61

MigrationBuilder

-0.61

twimg

-0.60

ViewStyle

-0.60

ReusableCell

-0.60

POSITIVE LOGITS

how

0.88

 ways

0.57

 whether

0.56

how

0.52

 bagaimana

0.52

cstdlib

0.50

 separately

0.50

amitié

0.49

如何

0.49

 كيف

0.48

Activations Density 0.820%

words related to academic investigations and discussions

No Comments

No Known Activations