INDEX

Explanations

references to health-related terms, particularly in the context of potential medical consequences

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

Code or non-English text

np_acts-logits-general · gemini-2.0-flash

reduced susceptibility

np_acts-logits-general · gemini-2.5-flash-lite

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

-0.66

©

-0.49

-0.48

-0.47

gre

-0.46

getDouble

-0.45

<b>

-0.43

<strong>

-0.41

POSITIVE LOGITS

 الرياضيه

0.85

Efq

0.84

VersionUID

0.80

 refroidissement

0.80

 nôtre

0.80

expandindo

0.78

 charité

0.78

 lokale

0.77

 ſeveral

0.77

 ainfi

0.77

Activations Density 0.009%

references to health-related terms, particularly in the context of potential medical consequences

Code or non-English text

reduced susceptibility

No Comments

No Known Activations