INDEX

Explanations

terms related to cognitive tasks and attention

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

DidLoad

-0.71

__(/*!

-0.68

expandindo

-0.67

IBOutlet

-0.67

IndentedString

-0.66

 ProtoMessage

-0.64

isholm

-0.58

bootstrapcdn

-0.56

 урна

-0.54

öglichkeiten

-0.54

POSITIVE LOGITS

 concentration

2.06

 Concentration

1.86

 attention

1.80

 concentrate

1.74

concentration

1.72

 focus

1.70

 concentrating

1.70

Concentration

1.69

 Attention

1.62

Concentr

1.62

Activations Density 0.303%

terms related to cognitive tasks and attention

No Comments

No Known Activations