INDEX

Explanations

first-person pronouns, indicating a focus on personal experiences or identity

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

for me or us

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

QUENCE

-0.64

 виправивши

-0.55

 plegable

-0.51

 дописавши

-0.51

 abstrato

-0.50

acité

-0.50

edicated

-0.49

 Witte

-0.48

 pensieri

-0.48

 navideño

-0.47

POSITIVE LOGITS

 endfor

0.60

 forKey

0.57

ForType

0.55

ForKey

0.49

for

0.47

tagHelperRunner

0.47

forKey

0.47

ؤلاء

0.46

ForValue

0.46

 fürs

0.45

Activations Density 0.014%

first-person pronouns, indicating a focus on personal experiences or identity

for me or us

No Comments

No Known Activations