INDEX

Explanations

patterns related to numerical data or values

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

hhhhhhhh

-0.94

 Wirt

-0.93

 tisch

-0.85

continence

-0.84

iclo

-0.83

 Bourgoin

-0.79

vuo

-0.79

saraba

-0.79

alaya

-0.78

SIO

-0.76

POSITIVE LOGITS

2.01

@"/

1.26

 Four

1.10

1.09

 FOUR

1.09

４

1.07

 Forty

1.05

FOUR

1.03

four

1.00

Activations Density 1.012%

patterns related to numerical data or values

No Comments

No Known Activations