INDEX

Explanations

references to political organizations and think tanks

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

preceding organizations or people

np_acts-logits-general · gemini-2.0-flash

think tanks and research institutes

np_acts-logits-general · gemini-2.5-flash-lite

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

المشاركات

-0.54

 Schilder

-0.49

Spoljašnje

-0.46

 ecles

-0.42

########.

-0.41

 CanadaChoose

-0.41

 propOrder

-0.40

ļ

-0.40

 calore

-0.39

MessageOf

-0.39

POSITIVE LOGITS

 think

1.10

 Policy

0.89

 policy

0.89

 Institute

0.86

 Center

0.84

 institute

0.83

 research

0.82

 Brookings

0.81

Policy

0.81

 Think

0.80

Activations Density 0.228%

references to political organizations and think tanks

preceding organizations or people

think tanks and research institutes

No Comments

No Known Activations