INDEX

Explanations

occurrences of the word "to" and its variations in different contexts involving movement or directionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

 distanciation

-0.69

theless

-0.68

 contextLoads

-0.68

 Flamengo

-0.67

jména

-0.67

 laikā

-0.67

思議

-0.66

Namara

-0.66

Calla

-0.66

TextBoxColumn

-0.64

POSITIVE LOGITS

TO

1.48

To

1.44

TO

1.38

To

1.31

to

1.28

to

1.27

DataTo

1.13

Toh

1.08

uto

1.04

yto

1.00

Activations Density 0.145%

occurrences of the word "to" and its variations in different contexts involving movement or directionality

No Comments

No Known Activations