INDEX

Explanations

terms related to risk and caution in health contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 EconPapers

-1.21

Personensuche

-1.03

 مرئيه

-0.97

ագրություններ

-0.96

verwijspagina

-0.90

tagHelperRunner

-0.89

 متعلقه

-0.88

 OFDb

-0.87

expandindo

-0.86

 Wiktionnaire

-0.86

POSITIVE LOGITS

↵↵↵

0.58

in

0.52

0.51

pro

0.50

im

0.50

lo

0.50

\\

0.49

вы

0.49

un

0.49

Activations Density 0.085%

terms related to risk and caution in health contexts

No Comments

No Known Activations