INDEX

Explanations

phrases indicating influence or effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 good

-0.54

pr

-0.53

 like

-0.52

too

-0.52

-0.49

bek

-0.48

 head

-0.47

ú

-0.47

POSITIVE LOGITS

########.

1.10

ThroughAttribute

1.10

MigrationBuilder

1.03

tagHelperRunner

0.88

RenderAtEndOf

0.88

)");

0.86

Portale

0.81

yntaxException

0.81

følgelig

0.80

 itſelf

0.77

Activations Density 0.514%

phrases indicating influence or effects

No Comments

No Known Activations