INDEX

Explanations

words related to membership in groups or organizations

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

 defaultstate

-1.02

 समीक्षक

-1.01

]--;

-0.99

NameInMap

-0.92

tagHelperRunner

-0.90

 Accesat

-0.88

 LoggerFactory

-0.87

thâu

-0.85

ValueStyle

-0.84

prefixer

-0.82

POSITIVE LOGITS

Members

0.71

 Members

0.71

 members

0.63

 Member

0.60

资格

0.57

 member

0.57

members

0.55

 MEMBER

0.55

 MEMBERS

0.54

Member

0.54

Activations Density 0.062%

words related to membership in groups or organizations

No Comments

No Known Activations