INDEX

Explanations

mentions of political entities and power dynamics

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

Follows "would," "to," or a comma

np_acts-logits-general · gemini-2.0-flash

modal verbs followed by verbs

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 transitioning

-0.92

 showcased

-0.89

 transitioned

-0.88

 showcasing

-0.88

 impactful

-0.86

 prioritizing

-0.83

 prioritize

-0.82

 prepping

-0.80

 prioritized

-0.80

 leveraging

-0.80

POSITIVE LOGITS

 skall

0.90

 daß

0.84

 läßt

0.83

 muß

0.78

faßt

0.73

 thereupon

0.71

 mußten

0.71

 Daß

0.71

MLLoader

0.70

 mußte

0.69

Activations Density 1.117%

mentions of political entities and power dynamics

Follows "would," "to," or a comma

modal verbs followed by verbs

No Comments

No Known Activations