INDEX

Explanations

segments that indicate external sources or links

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

RTEE

-0.91

 myſelf

-0.86

^(@)

-0.84

IntoConstraints

-0.83

ANDUM

-0.83

Datuak

-0.83

CWE

-0.79

__":

-0.77

/−

-0.76

 Cæsar

-0.74

POSITIVE LOGITS

…

1.25

...

1.20

....

1.00

….

1.00

……

0.98

…..

0.95

...(

0.94

…

0.87

.....

0.86

..

0.86

Activations Density 0.089%

segments that indicate external sources or links

No Comments

No Known Activations