INDEX

Explanations

variations of the word "to" indicating actions or movements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

-0.66

-0.60

-0.59

-0.57

-0.56

II

-0.56

POSITIVE LOGITS

 itſelf

1.41

^(@)

1.26

 Мексичка

1.25

 ―――――

1.25

 myſelf

1.23

 Савезне

1.22

 photolibrary

1.21

Personensuche

1.19

ChildScrollView

1.16

AddTagHelper

1.16

Activations Density 0.196%

variations of the word "to" indicating actions or movements

No Comments

No Known Activations