INDEX

Explanations

technical terms related to processing and systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 poffible

-0.74

 ویکی‌پدیای

-0.72

 Pingback

-0.65

msgTypes

-0.63

liceerd

-0.62

nocení

-0.60

 raiſ

-0.60

ducer

-0.59

NameInMap

-0.59

CloseOperation

-0.58

POSITIVE LOGITS

 häm

0.51

西亚

0.48

 apă

0.46

serde

0.46

 sved

0.45

毂

0.44

 pelear

0.43

 abandonné

0.42

vode

0.42

Abandon

0.42

Activations Density 0.077%

technical terms related to processing and systems

No Comments

No Known Activations