INDEX

Explanations

sections of text that contain data related to measurements or numeric values associated with 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 @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

ogia

-0.60

delwed

-0.58

 AssemblyTitle

-0.58

 Unsc

-0.53

paux

-0.50

SpringBootTest

-0.49

artifactId

-0.47

Kui

-0.46

addGap

-0.46

OutputPath

-0.46

POSITIVE LOGITS

 primaire

0.70

 primary

0.69

 OFDb

0.68

Primary

0.67

 Primary

0.66

 primaria

0.65

WebVitals

0.65

primary

0.64

 Primaria

0.64

 primaries

0.64

Activations Density 0.520%

sections of text that contain data related to measurements or numeric values associated with health indicators

No Comments

No Known Activations