INDEX

Explanations

scientific measurements and parameters in research studies

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

########.

-0.60

 ejecut

-0.49

andExpect

-0.48

 يتيمه

-0.48

 viendra

-0.48

fú

-0.46

 dred

-0.46

 amnesty

-0.46

extAlignment

-0.46

Expensive

-0.45

POSITIVE LOGITS

 total

1.53

 average

1.47

 mean

1.26

 maximum

1.18

total

1.14

average

1.14

 Total

1.13

 Average

1.09

Average

1.07

 median

1.01

Activations Density 2.765%

scientific measurements and parameters in research studies

No Comments

No Known Activations