INDEX

Explanations

medical texts mentioning "hospital", "referral", "units", and/or "NHS"

oai_token-act-pair · gemini-2.0-flash

references to trust or related terms

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

hospitals

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 making

-0.58

 MAKING

-0.54

 made

-0.53

MAKING

-0.51

 makes

-0.50

 make

-0.50

 MADE

-0.50

 calendriers

-0.50

 оригіналу

-0.50

made

-0.50

POSITIVE LOGITS

 ***!

0.61

 Trusts

0.56

 Trust

0.54

 trusts

0.54

xmlhttp

0.54

 trust

0.54

resave

0.54

 autorytatywna

0.53

 esboço

0.52

 ThemeData

0.52

Activations Density 1.318%

medical texts mentioning "hospital", "referral", "units", and/or "NHS"

references to trust or related terms

hospitals

No Comments

No Known Activations