INDEX

Explanations

references to legal entities or figures, particularly involving court and plaintiff matters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

étaire

-0.70

zeptember

-0.66

 Hirst

-0.64

 McCann

-0.64

érance

-0.64

ξης

-0.64

Kw

-0.62

لاثة

-0.60

 OnInit

-0.60

mur

-0.60

POSITIVE LOGITS

</blockquote>

1.97

</h5>

1.15

</h1>

1.09

</table>

1.07

</h6>

1.03

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

1.03

↵↵↵↵

1.03

findpost

1.00

</h4>

0.99

↵↵↵↵↵↵↵↵

0.98

Activations Density 0.019%

references to legal entities or figures, particularly involving court and plaintiff matters

No Comments

No Known Activations