INDEX

Explanations

ellipses or omissions in conversation or text indicating pauses or trailing off thoughts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ſhip

-0.80

nefs

-0.75

.")

-0.73

{}'.

-0.72

$")

-0.71

-0.70

}</

-0.70

chränk

-0.70

)");

-0.70

/>";

-0.70

POSITIVE LOGITS

...

1.87

...

1.40

…

1.38

 ....

1.34

....

1.33

!...

1.16

,...

1.13

.....

1.09

......

1.08

 […]

1.07

Activations Density 0.108%

ellipses or omissions in conversation or text indicating pauses or trailing off thoughts

No Comments

No Known Activations