INDEX

Explanations

interrogative phrases and words that seek clarification or information

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

-0.47

 hold

-0.46

Co

-0.46

hold

-0.45

 spot

-0.41

 multiple

-0.41

 said

-0.41

 modelAndView

-0.40

↵↵

-0.39

POSITIVE LOGITS

IntoConstraints

1.01

Personendaten

0.96

 متعلقه

0.96

RenderAtEndOf

0.94

 мәкал

0.88

MigrationBuilder

0.87

 AssemblyTitle

0.86

 MainAxisSize

0.86

 мәкалә

0.86

 مشين

0.85

Activations Density 0.240%

interrogative phrases and words that seek clarification or information

No Known Activations