INDEX

Explanations

key terms related to biological processes and health indicators

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Lähteet

-0.59

Hrsg

-0.53

liferay

-0.51

Története

-0.49

 onCreateView

-0.49

]--;

-0.47

tų

-0.46

itatis

-0.46

tizo

-0.46

bės

-0.45

POSITIVE LOGITS

place

0.90

 houſe

0.81

work

0.78

ſelves

0.77

case

0.74

works

0.69

ſelf

0.69

 ſtate

0.69

board

0.69

ſy

0.67

Activations Density 0.493%

key terms related to biological processes and health indicators

No Comments

No Known Activations