INDEX

Explanations

highly repetitive or patterned sequences in text

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

fromLTRB

-0.89

Berna

-0.88

bosis

-0.80

Portale

-0.80

 Sink

-0.79

 ?>">

-0.78

.'/

-0.77

м

-0.75

tioner

-0.74

mib

-0.73

POSITIVE LOGITS

1.21

 fotografico

1.03

іод

0.86

 Marjorie

0.83

 anteriore

0.82

 giuri

0.82

 sœur

0.82

 Gentry

0.81

 jurídico

0.80

 Emory

0.80

Activations Density 0.063%

highly repetitive or patterned sequences in text

No Comments

No Known Activations