INDEX

Explanations

phrases that indicate medical evaluations or assessments

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

Code snippets and web addresses

np_acts-logits-general · gemini-2.0-flash

programming code and URLs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 idéia

-0.64

-0.61

("

-0.55

 http

-0.53

</s>

-0.53

%)$

-0.51

veo

-0.49

).(

-0.48

 daß

-0.48

 greatest

-0.48

POSITIVE LOGITS

 autorytatywna

0.98

 Afterward

0.97

 obstante

0.93

AndEndTag

0.92

Personensuche

0.92

Moreover

0.89

 Asimismo

0.86

 Moreover

0.85

 Notably

0.85

abestanden

0.82

Activations Density 0.064%

phrases that indicate medical evaluations or assessments

Code snippets and web addresses

programming code and URLs

No Comments

No Known Activations