INDEX

Explanations

names of specific plants and their parts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

orsese

-0.52

mphony

-0.49

 Rica

-0.49

ReusableCell

-0.48

setGeometry

-0.48

AsUp

-0.47

ليه

-0.46

UrlResolution

-0.45

msgSender

-0.44

schild

-0.44

POSITIVE LOGITS

Tikang

0.79

joba

0.76

granate

0.75

écou

0.67

urgeon

0.66

IVEREF

0.65

mappedBy

0.63

 fubject

0.59

Lavender

0.58

 primaries

0.58

Activations Density 0.278%

names of specific plants and their parts

No Comments

No Known Activations