INDEX

Explanations

future tense verbs indicating planned actions or events

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

future events planned

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

wuchs

-0.36

 Roberts

-0.33

 Indicate

-0.32

 last

-0.32

aren

-0.31

 subsequent

-0.31

 Condition

-0.31

the

-0.31

 Good

-0.30

POSITIVE LOGITS

ьаж

0.71

 للاسماء

0.68

expandindo

0.68

enschappelijke

0.60

WithIOException

0.59

 Biôgrafia

0.59

 ModelExpression

0.59

сылкі

0.57

 arşivlendi

0.56

MLLoader

0.55

Activations Density 0.021%

future tense verbs indicating planned actions or events

future events planned

No Comments

No Known Activations