INDEX

Explanations

references to district courts or related judicial terms

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

NESSEE

-0.75

sendMail

-0.74

 अव

-0.71

 fumes

-0.70

BeanUtils

-0.69

 Programmer

-0.69

>//

-0.68

carolina

-0.67

 canoes

-0.65

 aliqu

-0.64

POSITIVE LOGITS

 district

2.25

 District

2.19

 DISTRICT

2.08

 districts

2.07

District

2.06

district

1.94

DISTRICT

1.93

 Districts

1.87

districts

1.74

ricts

1.41

Activations Density 0.073%

references to district courts or related judicial terms

No Comments

No Known Activations