INDEX

Explanations

expressions of agreement or affirmation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MLLoader

-0.66

__()

-0.62

)*/

-0.61

 '\\;'

-0.61

Datuak

-0.58

μως

-0.58

}-${

-0.57

 Alcott

-0.56

larak

-0.56

клопе

-0.56

POSITIVE LOGITS

 yeah

1.09

Yeah

0.99

 Yeah

0.98

yeah

0.91

 sure

0.89

 YEAH

0.79

hhh

0.77

Yea

0.74

hh

0.73

Sure

0.72

Activations Density 0.045%

expressions of agreement or affirmation

No Comments

No Known Activations