INDEX

Explanations

symbols or notation related to research methodology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

AndEndTag

-0.65

�

-0.64



-0.60

 conci

-0.59

dür

-0.58

Bø

-0.58

جغرافيا

-0.58

ínű

-0.56

%)$

-0.55

findpost

-0.54

POSITIVE LOGITS

————————

0.97

.^

0.97

————————————————

0.95

:^

0.86

/^

0.85

"^

0.85

})^

0.85

——————

0.84

————

0.84

—————

0.84

Activations Density 0.663%

symbols or notation related to research methodology

No Comments

No Known Activations