INDEX

Explanations

references to political actions and legislative processes

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

StoryboardSegue

-0.62

RenderAtEndOf

-0.57

 Istri

-0.54

hock

-0.54

irtschaft

-0.53

طبيق

-0.51

IntoConstraints

-0.50

-0.48

yntaxException

-0.48

PLW

-0.48

POSITIVE LOGITS

 senator

1.35

 senators

1.30

 Senator

1.29

 Senate

1.26

Senator

1.22

Sen

1.22

Sen

1.20

 Senators

1.19

sen

1.15

 Sens

1.10

Activations Density 0.106%

references to political actions and legislative processes

No Comments

No Known Activations