INDEX

Explanations

instances of the term "reverse" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/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.0.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

 Numerade

-0.45

 surla

-0.44

 autorité

-0.43

 apsau

-0.42

 czę

-0.40

 ferons

-0.39

niów

-0.38

CppCodeGen

-0.38

cją

-0.37

yarnpkg

-0.35

POSITIVE LOGITS

 reverse

0.71

reverse

0.67

Ari

0.64

"__

0.58

 buckets

0.57

 slapped

0.57

Ari

0.57

 backwards

0.55

 curtains

0.55

 ujednoznacz

0.55

Activations Density 0.199%

instances of the term "reverse" in various contexts

No Comments

No Known Activations