INDEX

Explanations

fillers or hesitations in speech

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

expandindo

-0.73

]='\

-0.72

Portail

-0.69

ientôt

-0.68

--*/

-0.66

KommentareTeilen

-0.65

ChildScrollView

-0.64

 kond

-0.64

AccessFile

-0.63

basicConfig

-0.63

POSITIVE LOGITS

Um

0.69

uh

0.59

Uh

0.58

Uhm

0.56

um

0.56

ums

0.52

UM

0.51

UM

0.50

umm

0.50

ReferenceEquals

0.50

Activations Density 0.064%

fillers or hesitations in speech

No Comments

No Known Activations