INDEX

Explanations

references to specific individuals

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

Capitalized names followed by "said" or similar verbs

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

хьтан

-0.48

 réaliste

-0.46

 financeira

-0.46

alyptus

-0.45

 område

-0.45

 naturen

-0.44

 elétrica

-0.44

 kautta

-0.42

 uovo

-0.42

følgelig

-0.42

POSITIVE LOGITS

 himself

0.78

himself

0.68

 nakalista

0.52

 EconPapers

0.51

AddTagHelper

0.49

 pulumi

0.48

참고

0.47

 ExecuteAsync

0.47

anyahu

0.47

 himſelf

0.47

Activations Density 0.289%

references to specific individuals

Capitalized names followed by "said" or similar verbs

No Comments

No Known Activations