INDEX

Explanations

phrases indicating claims, objections, and reports in legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

UnsafeEnabled

-0.47

theless

-0.46

aktur

-0.46

zoll

-0.45

tijden

-0.45

 coronavirus

-0.45

 Nuova

-0.45

İstinadlar

-0.45

ISB

-0.44

 Himmel

-0.43

POSITIVE LOGITS

ThroughAttribute

0.66

BeginContext

0.64

Autoritní

0.64

 فريبيس

0.63

findpost

0.62

 تضيفلها

0.60

+#+#

0.60

EDEFAULT

0.59

 Exactos

0.59

хьтан

0.57

Activations Density 2.784%

phrases indicating claims, objections, and reports in legal contexts

No Comments

No Known Activations