INDEX

Explanations

occurrences of the word "it"

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

"It" followed by a verb

np_acts-logits-general · gemini-2.0-flash

It 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

AndEndTag

-0.75

garh

-0.64

 pulumi

-0.64

 HttpNotFound

-0.62

solicited

-0.61

werve

-0.59

duled

-0.59

WireFormatLite

-0.59

righted

-0.58

MemoryWarning

-0.57

POSITIVE LOGITS

########.

0.60

 seems

0.58

 mungkin

0.56

 wasn

0.56

 ऐसा

0.54

 turns

0.54

Turns

0.51

 parece

0.50

 Turns

0.50

ու

0.48

Activations Density 0.152%

occurrences of the word "it"

"It" followed by a verb

It followed by verbs

No Comments

No Known Activations