INDEX

Explanations

usages of the word "to" and its various forms in different contexts

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

verbs after "to"

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

WriteLiteral

-0.57

-0.49

 autorytatywna

-0.48

 насељу

-0.48

 Мексичка

-0.47

afficheront

-0.47

spl

-0.45

 laboring

-0.44

 transfieras

-0.44

httphttps

-0.44

POSITIVE LOGITS

ukkig

0.46

 Correspond

0.43

PreInfinity

0.41

)_/¯

0.40

ifflin

0.40

 jangan

0.39

 proportionally

0.39

⟬

0.38

 Proportion

0.38

ニュアル

0.38

Activations Density 0.003%

usages of the word "to" and its various forms in different contexts

verbs after "to"

No Comments

No Known Activations