INDEX

Explanations

phrases indicating actions and their consequences, particularly in relation to choices and recommendations

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

Followed by a noun

np_acts-logits-general · gemini-2.0-flash

those, areas, situations

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

libft

-0.56

 oprot

-0.54

AndEndTag

-0.52

 wikipagina

-0.51

PreferredItem

-0.50

 poveznice

-0.49

IndentedString

-0.49

❋

-0.49

StoreMessageInfo

-0.48

 respectivos

-0.48

POSITIVE LOGITS

 situations

1.11

 those

1.05

 areas

1.04

 aquellas

0.99

 aquellos

0.97

 something

0.96

 items

0.96

 olyan

0.93

 những

0.92

 ones

0.91

Activations Density 1.391%

phrases indicating actions and their consequences, particularly in relation to choices and recommendations

Followed by a noun

those, areas, situations

No Comments

No Known Activations