INDEX

Explanations

proper nouns, specifically names of people and locations

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

__).

-0.53

 recuperação

-0.52

 action

-0.48

 propriedade

-0.47

 Auft

-0.43

hat

-0.42

outcome

-0.42

 ação

-0.41

uelve

-0.41

CELL

-0.41

POSITIVE LOGITS

SharedDtor

0.86

 <<<<<<<<<<<<<<

0.82

 correctes

0.74

ArgsConstructor

0.73

WriteTagHelper

0.71

providedIn

0.69

发表于

0.68

 esternos

0.68

ItemLayout

0.64

AndEndTag

0.63

Activations Density 0.218%

proper nouns, specifically names of people and locations

No Comments

No Known Activations