INDEX

Explanations

rhetorical questions and discussions about reasoning

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

Follows a statement needing further explanation

np_acts-logits-general · gemini-2.0-flash

explaining why or giving reasons

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

migrationBuilder

-0.60

TestTools

-0.60

úgó

-0.56

argout

-0.54

jsonwebtoken

-0.53

 useStyles

-0.53

parency

-0.52

évaluateur

-0.52

ⓘ

-0.51

COUVER

-0.49

POSITIVE LOGITS

 reason

1.70

 because

1.69

 reasons

1.55

because

1.52

理由は

1.49

 perché

1.47

reason

1.41

 Çünkü

1.40

why

1.39

なぜ

1.39

Activations Density 0.461%

rhetorical questions and discussions about reasoning

Follows a statement needing further explanation

explaining why or giving reasons

No Comments

No Known Activations