INDEX

Explanations

terms related to civil issues and civil rights

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

 Monfieur

-0.79

็จ

-0.78

 Krakowie

-0.77

 itſelf

-0.76

 becauſe

-0.74

 myſelf

-0.74

RetentionPolicy

-0.73

 themſelves

-0.72

Efq

-0.70

ſelf

-0.70

POSITIVE LOGITS

 civil

1.14

 Civil

1.05

Civil

0.98

civil

0.90

 CIVIL

0.80

 society

0.64

CIV

0.62

 rights

0.60

yet

0.58

 servants

0.55

Activations Density 0.046%

terms related to civil issues and civil rights

No Comments

No Known Activations