INDEX

Explanations

pronouns and references to individuals in personal narratives or discussions

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

Pronouns followed by past tense verbs

np_acts-logits-general · gemini-2.0-flash

pronouns followed by auxiliary verbs and "did"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 AssemblyProduct

-0.86

ValueStyle

-0.58

Campeonato

-0.56

fromnode

-0.50

 reproach

-0.48

 geçi

-0.48

Kariera

-0.47

 ballon

-0.47

rtz

-0.47

EXPRESSION

-0.47

POSITIVE LOGITS

TargetException

0.62

 feel

0.62

HostException

0.60

LLocation

0.59

 think

0.58

)&&

0.58

 thinks

0.58

ReusableCell

0.58

 myſelf

0.57

extAlignment

0.57

Activations Density 0.234%

pronouns and references to individuals in personal narratives or discussions

Pronouns followed by past tense verbs

pronouns followed by auxiliary verbs and "did"

No Comments

No Known Activations