INDEX

Explanations

occurrences of the word "all"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.38.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

 overall

-0.45

 allemaal

-0.44

jenigen

-0.42

呢

-0.41

 모두

-0.41

Overall

-0.40

 Overall

-0.39

tagHelperRunner

-0.39

 always

-0.38

UpInside

-0.38

POSITIVE LOGITS

 sorts

1.25

 kinds

1.09

 manner

0.88

kinds

0.77

uding

0.76

llll

0.70

lll

0.70

yship

0.68

manner

0.68

iteration

0.68

Activations Density 0.159%

occurrences of the word "all"

No Comments

No Known Activations