INDEX

Explanations

events or actions related to death, discovery, or significant happenings in a narrative context

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

ModelAdmin

-0.51

pulumi

-0.50

extAlignment

-0.50

HasForeignKey

-0.49

setVerticalGroup

-0.49

ietf

-0.48

yaxis

-0.48

RouterModule

-0.46

'];?>

-0.45

,:);

-0.45

POSITIVE LOGITS

 before

1.15

时

1.12

 after

1.07

時

1.07

后

1.06

after

1.03

之后

1.03

的时候

1.00

 afterward

1.00

时候

0.99

Activations Density 0.044%

events or actions related to death, discovery, or significant happenings in a narrative context

No Comments

No Known Activations