INDEX

Explanations

occurrences of the word "the."

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Efq

-1.25

 itſelf

-1.09

 AspNetCore

-0.99

 myſelf

-0.98

 Monfieur

-0.95

 fhew

-0.94

^(@)

-0.92

 Jefus

-0.91

 raiſ

-0.88

ſelf

-0.86

POSITIVE LOGITS

必

0.50

 phá

0.46

AtIndex

0.44

orteur

0.44

if

0.44

ischem

0.43

as

0.43

ter

0.43

plat

0.42

Index

0.42

Activations Density 0.001%

occurrences of the word "the."

No Comments

No Known Activations

occurrences of the word "the."

No Comments

No Known Activations