INDEX

Explanations

phrases that indicate relationships, references, and contextual connections in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AttributeSet

-1.23

endphp

-1.02

 متعلقه

-0.97

 مشين

-0.89

脚注の使い方

-0.85

存于互联网档案馆

-0.81

SBATCH

-0.81

ReusableCell

-0.79

AnchorStyles

-0.77

 <<<<<<<<<<<<<<

-0.76

POSITIVE LOGITS

<eos>

0.49

 lumea

0.47

 argint

0.46

titleMargin

0.46

هما

0.43

 понравился

0.43

 ulang

0.43

 umgekehrt

0.42

↵↵

0.41

Activations Density 0.756%

phrases that indicate relationships, references, and contextual connections in the text

No Comments

No Known Activations