INDEX

Explanations

phrases related to searching for something or expressing a need

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

dega

-0.56

큼

-0.56

nessed

-0.53

abestanden

-0.52

 kasarigan

-0.47

hdys

-0.46



-0.46

 مواليد

-0.44

fördert

-0.44

Zay

-0.43

POSITIVE LOGITS

 search

2.93

 searching

2.60

search

2.42

 searches

2.37

 Search

2.34

 SEARCH

2.31

 Searching

2.25

Search

2.19

searching

2.16

 hunt

2.16

Activations Density 0.488%

phrases related to searching for something or expressing a need

No Comments

No Known Activations