INDEX

Explanations

specific entities and actions related to legal and forensic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

the

-0.65

 about

-0.62

-0.57

 these

-0.53

 this

-0.51

hene

-0.51

-0.50

ématique

-0.48

anzas

-0.47

in

-0.45

POSITIVE LOGITS

parsedMessage

0.79

 transfieras

0.77

DoubleQuotes

0.76

 متعلقه

0.73

Cyfeiriadau

0.72

///</

0.71

 bezeichneter

0.71

 Administrativna

0.70

IUrlHelper

0.69

 հղումներ

0.69

Activations Density 0.118%

specific entities and actions related to legal and forensic contexts

No Comments

No Known Activations