INDEX

Explanations

instances of the word "remember" and variations of its usage

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

memory recall

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

AndroidJUnit

-0.50

 Савезне

-0.38

 frères

-0.33

 hjelp

-0.33

 écl

-0.33

 BrowserModule

-0.32

liehen

-0.32

true

-0.32

 оригіналу

-0.31

 dépos

-0.30

POSITIVE LOGITS

 remembered

0.77

remember

0.73

 remember

0.71

 amnesia

0.68

 recollections

0.67



0.66

 memory

0.66

 recall

0.66

 recollection

0.66

 forgotten

0.65

Activations Density 0.010%

instances of the word "remember" and variations of its usage

memory recall

No Comments

No Known Activations