INDEX

Explanations

phrases indicating the search for information or clarification

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

after verbs of perception or discovery

np_acts-logits-general · gemini-2.0-flash

finding and discovery

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

usermodel

-0.59

 last

-0.58

########.

-0.56

cshtml

-0.56

sendStatus

-0.56

glTexCoord

-0.55

ungkin

-0.54

ContextHolder

-0.54

 DriverManager

-0.54

 Last

-0.53

POSITIVE LOGITS

 discovered

1.36

 found

1.36

发现

1.25

 выясни

1.22

 discovers

1.17

 оказалось

1.15

發現

1.14

 ternyata

1.13

found

1.12

 discover

1.08

Activations Density 0.520%

phrases indicating the search for information or clarification

after verbs of perception or discovery

finding and discovery

No Comments

No Known Activations

phrases indicating the search for information or clarification

after verbs of perception or discovery

finding and discovery

No Comments

No Known Activations