INDEX

Explanations

interrogative words and phrases that seek clarification or choice

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

-0.57

 فريبيس

-0.57

 endwhile

-0.57

StructEnd

-0.57

 său

-0.54

sizeCache

-0.53

 őket

-0.53

adaptiveStyles

-0.52

 itself

-0.51

 suivantes

-0.50

POSITIVE LOGITS

 kind

0.81

 kinds

0.80

 version

0.69

 parts

0.68

 sorts

0.68

 type

0.67

 direction

0.64

 Theſe

0.64

 कैसी

0.64

Quels

0.64

Activations Density 0.118%

interrogative words and phrases that seek clarification or choice

No Comments

No Known Activations