INDEX

Explanations

expressions related to uncertainty or recalling memories

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

"I" followed by a verb implying thought or memory

np_acts-logits-general · gemini-2.0-flash

thoughts on memory and recall

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

autant

-0.52

DockStyle

-0.50

makedirs

-0.49

ertale

-0.49

makeText

-0.48

GeneratedValue

-0.47

hoga

-0.47

CloseOperation

-0.44

iaceae

-0.43

 merchandise

-0.43

POSITIVE LOGITS

 memory

0.97

 IIRC

0.97

 iirc

0.95

 remember

0.94

 recall

0.91

 recollection

0.86

memory

0.85

好像是

0.84

forgot

0.84

forget

0.81

Activations Density 0.200%

expressions related to uncertainty or recalling memories

"I" followed by a verb implying thought or memory

thoughts on memory and recall

No Comments

No Known Activations