INDEX

Explanations

specific instances of medical and healthcare terms

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

Followed by verbs

np_acts-logits-general · gemini-2.0-flash

historical grants and dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 Cæsar

-0.66

 something

-0.64

 must

-0.59

 simply

-0.58

 purpoſe

-0.58

 Indeed

-0.57

 creatives

-0.56

 user

-0.56

 Diſ

-0.55

yes

-0.55

POSITIVE LOGITS

LabelTagHelper

0.78

 następnie

0.73

 invokingState

0.73

SharedCtor

0.67

 Потом

0.67

UpInside

0.65

PerformLayout

0.65

InjectAttribute

0.64

 '\\;'

0.64

 posteriormente

0.64

Activations Density 0.185%

specific instances of medical and healthcare terms

Followed by verbs

historical grants and dates

No Comments

No Known Activations