INDEX

Explanations

rhetorical questions and affirmative/negative responses in conversations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 alright

-0.57

 AssemblyProduct

-0.56

 True

-0.56

 AssemblyCulture

-0.56

GOTREF

-0.56

Rohy

-0.55

MigrationBuilder

-0.55

ok

-0.55

true

-0.52

trum

-0.52

POSITIVE LOGITS

Absolutely

1.15

 absolutely

1.14

 Absolutely

1.13

 Nope

1.11

absolutely

1.11

Nope

1.05

nope

1.00

 nope

0.99

 assolutamente

0.93

 absolument

0.90

Activations Density 0.179%

rhetorical questions and affirmative/negative responses in conversations

No Comments

No Known Activations