INDEX

Explanations

references to additional information or follow-up actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Wikispecies

-0.63

 Roskov

-0.60

 ArrayAdapter

-0.59

 оригіналу

-0.59

ГЛА

-0.58

 consultato

-0.56

Rhestr

-0.56

openConnection

-0.56

ModelAdmin

-0.56

manjaro

-0.56

POSITIVE LOGITS

 further

0.65

进一步

0.64

Further

0.64

further

0.63

MORE

0.61

more

0.60

 Further

0.59

继续

0.58

More

0.57

 more

0.56

Activations Density 0.399%

references to additional information or follow-up actions

No Comments

No Known Activations