INDEX

Explanations

terms related to earning and financial benefits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Schroeder

-0.66

Ag

-0.64

Aholisi

-0.64

Sp

-0.64

 idea

-0.63

 opge

-0.62

 Porter

-0.62

InputText

-0.62

 Conroy

-0.62

MemoryWarning

-0.61

POSITIVE LOGITS

 earn

2.23

 earned

2.21

 earns

2.09

Earn

2.09

 Earned

2.07

 earning

2.05

 Earn

2.04

earned

2.03

earning

1.80

earn

1.72

Activations Density 0.076%

terms related to earning and financial benefits

No Comments

No Known Activations