INDEX

Explanations

specific locations, particularly focusing on the preposition "at."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

leſs

-0.64

 myſelf

-0.61



-0.60

horabuena

-0.60

StoryboardSegue

-0.57

 recomp

-0.57

Rico

-0.56

 itſelf

-0.55

 civilisation

-0.55

 anſ

-0.55

POSITIVE LOGITS

at

1.17

At

0.97

At

0.90

at

0.85

AT

0.75

[@

0.60

AT

0.60

0.57

 Tại

0.57

 tại

0.55

Activations Density 0.353%

specific locations, particularly focusing on the preposition "at."

No Comments

No Known Activations