INDEX

Explanations

instances of the word "in."

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

Follows "In" or "in"

np_acts-logits-general · gemini-2.0-flash

in + transition words

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

transQ

-0.51

ResumeLayout

-0.51

 Escolar

-0.48

 pinulongan

-0.48

 mostly

-0.48

 perhaps

-0.47

possibly

-0.46

essentially

-0.45

HEAST

-0.45

metti

-0.45

POSITIVE LOGITS

StoryboardSegue

0.64

:"-"`

0.63

 view

0.59

 case

0.59

Hozzáférés

0.59

extendable

0.57

Furthermore

0.57

 IndexPath

0.57

 fact

0.55

 consequence

0.55

Activations Density 0.339%

instances of the word "in."

Follows "In" or "in"

in + transition words

No Comments

No Known Activations