INDEX

Explanations

specific medical terms and variables related to health studies and statistics

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

Abbreviations or acronyms starting with "L"

np_acts-logits-general · gemini-2.0-flash

L-initial acronyms

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

➯

-0.49

 CreateTagHelper

-0.48

 MainAxisSize

-0.47

 OMITBAD

-0.46

 مشين

-0.45

intios

-0.43

évaluateur

-0.41

riwal

-0.41

AccessorTable

-0.40

 Brim

-0.39

POSITIVE LOGITS

LC

1.25

LM

1.20

LP

1.19

LR

1.14

LF

1.13

LU

1.13

LB

1.13

LO

1.13

LK

1.13

LH

1.13

Activations Density 2.168%

specific medical terms and variables related to health studies and statistics

Abbreviations or acronyms starting with "L"

L-initial acronyms

No Comments

No Known Activations