INDEX

Explanations

terms related to medical conditions and treatments

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

Word after "to" followed by a negative consequence

np_acts-logits-general · gemini-2.0-flash

damage or dysfunction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

PhysRev

-0.58

 bổ

-0.56

tiera

-0.55

 كومونز

-0.53

 Belong

-0.52

 Zufall

-0.51

setParent

-0.50

 disiplin

-0.49

 上下

-0.48

 compleanno

-0.48

POSITIVE LOGITS

 impaired

1.10

 alterations

1.03

 decreased

1.01

 altered

1.01

 abnormal

0.99

 reduced

0.97

 abnormalities

0.96

 impairment

0.94

 alteration

0.93

 increased

0.87

Activations Density 1.686%

terms related to medical conditions and treatments

Word after "to" followed by a negative consequence

damage or dysfunction

No Comments

No Known Activations