INDEX

Explanations

phrases related to significant consequences and impacts of decisions or actions

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

Negative consequences or effects

np_acts-logits-general · gemini-2.0-flash

verbs followed by outcomes

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

-0.71

posób

-0.69

awtextra

-0.68

HasForeignKey

-0.68

uesia

-0.66

ValueStyle

-0.66

 ModelExpression

-0.65

forChild

-0.65

setVerticalGroup

-0.65

torie

-0.65

POSITIVE LOGITS

 impact

2.36

 impacts

2.21

 consequences

2.09

 effects

2.03

impact

1.99

 Impact

1.97

Impact

1.93

 effect

1.89

 Effects

1.85

 Impacts

1.83

Activations Density 0.597%

phrases related to significant consequences and impacts of decisions or actions

Negative consequences or effects

verbs followed by outcomes

No Comments

No Known Activations