INDEX

Explanations

the word "is" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

CloseOperation

-1.13

nextProps

-1.11

 ſeveral

-1.05

 ſever

-1.02

 themſelves

-0.98

 houſe

-0.97

 Houſe

-0.94

 myſelf

-0.94

 raiſ

-0.94

 BoxDecoration

-0.93

POSITIVE LOGITS

Is

1.39

IS

1.28

Is

1.26

is

1.23

bIs

1.14

 setIs

1.14

mIs

1.12

is

1.09

IS

0.98

 getIs

0.94

Activations Density 0.150%

the word "is" in various contexts

No Comments

No Known Activations