INDEX

Explanations

references to graphic-related content

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

MessageOf

-0.99

providedIn

-0.96

NameInMap

-0.93

GEBURTSDATUM

-0.90

 يتيمه

-0.89

MeasureSpec

-0.87

tableFuture

-0.87

awaiter

-0.87

KEYCODE

-0.85

ertale

-0.85

POSITIVE LOGITS

 graphics

2.10

 graphic

1.87

graphics

1.86

 Graphics

1.78

Graphics

1.71

graphic

1.67

 Graphic

1.64

 GRAPH

1.56

GRAPHIC

1.55

Graphic

1.51

Activations Density 0.067%

references to graphic-related content

No Comments

No Known Activations