INDEX

Explanations

phrases that indicate the structure, organization, or summary of information

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

 disambiguazione

-0.96

AndEndTag

-0.94

PreferredItem

-0.73

WithIOException

-0.71

StoryboardSegue

-0.67

 MenuView

-0.61

dersfield

-0.57

atchewan

-0.57

OGND

-0.56

DebuggerStep

-0.56

POSITIVE LOGITS

 follows

1.58

as

1.39

follows

1.28

如下

1.01

 Follows

1.00

 sebagai

0.96

 follow

0.94

follow

0.86

 כד

0.86

 volgt

0.85

Activations Density 0.510%

phrases that indicate the structure, organization, or summary of information

No Comments

No Known Activations