INDEX

Explanations

concepts related to hidden or concealed elements

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

"hidden" followed by "ar" or "auto"

np_acts-logits-general · gemini-2.0-flash

hidden auto-regressive, hidden hunger, hide away

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

WindowConstants

-0.65

setVerticalGroup

-0.59

 بيها

-0.58

CWE

-0.57

AdapterView

-0.56

waz

-0.54

Diz

-0.53

 BorderRadius

-0.53

chige

-0.52

ItemBackground

-0.52

POSITIVE LOGITS

MethodManager

0.87

hid

0.84

 behind

0.80

 secrets

0.79

 hiding

0.78

Secrets

0.78

 hidden

0.77

 Hidden

0.76

 hide

0.76

HIDDEN

0.75

Activations Density 0.238%

concepts related to hidden or concealed elements

"hidden" followed by "ar" or "auto"

hidden auto-regressive, hidden hunger, hide away

No Comments

No Known Activations