INDEX

Explanations

words and phrases related to medical studies and healthcare

oai_token-act-pair · gemini-2.0-flash

uncommon medical terms or jargon

np_token-act-pair-logits · gpt-4o-mini

Business/Healthcare/Workers

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ainfi

-0.73

complexContent

-0.67

 étoit

-0.65

 auffi

-0.61

 myſelf

-0.59

 quæ

-0.58

 themſelves

-0.58

 avoit

-0.58

 Theſe

-0.57

 becauſe

-0.57

POSITIVE LOGITS

 оригіналу

0.59

BeginContext

0.55

DotNetBar

0.54

спеди

0.54

enance

0.52

twimg

0.50

gnancy

0.50

Aktualisiert

0.50

دانشنامهٔ

0.49

стат

0.49

Activations Density 2.915%

words and phrases related to medical studies and healthcare

uncommon medical terms or jargon

Business/Healthcare/Workers

No Comments

No Known Activations