INDEX

Explanations

phrases indicating job performance and evaluation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

出版年

-0.72

 ISNI

-0.52

specifier

-0.52

 histórica

-0.48

/></

-0.46

RequestParam

-0.46

alva

-0.46

laim

-0.45

 invalidate

-0.45

EXTERN

-0.45

POSITIVE LOGITS

 adjustment

1.57

 adjusting

1.46

 settling

1.40

 Adjustment

1.39

 adapting

1.39

 adaptation

1.38

 Adjusting

1.36

Adjust

1.32

adjustment

1.32

 adjust

1.28

Activations Density 0.294%

phrases indicating job performance and evaluation

No Comments

No Known Activations