INDEX

Explanations

questions and negative statements

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

antMatchers

-1.12

 שוליים

-0.99

 itſelf

-0.88

Composable

-0.88

 Rhonda

-0.88

 Grau

-0.88

InputBorder

-0.86

 Houſe

-0.86

Ise

-0.86

 houſe

-0.85

POSITIVE LOGITS

did

1.73

Did

1.70

did

1.67

DID

1.64

Did

1.54

DID

1.48

 Didi

1.21

 didn

1.04

 Didn

1.01

 done

0.98

Activations Density 0.091%

questions and negative statements

No Comments

No Known Activations