INDEX

Explanations

phrases that mention inclusion criteria or standards in research studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

↵↵

-0.53

ha

-0.42

ニーカー

-0.38

-0.36

ammen

-0.35

Finally

-0.34

Lastly

-0.33

ことが

-0.32

jam

-0.32

↵↵↵

-0.31

POSITIVE LOGITS

 nakalista

1.29

 насељу

1.12

parsedMessage

1.03

findpost

1.00

GEBURTSDATUM

0.99

expandindo

0.99

tvguidetime

0.99

StoryboardSegue

0.97

 <<<<<<<<<<<<<<

0.96

 CURIAM

0.96

Activations Density 0.280%

phrases that mention inclusion criteria or standards in research studies

No Comments

No Known Activations