INDEX

Explanations

intensifiers that emphasize the degree of the adjectives or adverbs in the text

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

intensifier followed by adjective or adverb

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

Билгалдахарш

-0.57

ScopeManager

-0.52

 fronteras

-0.50

 huelga

-0.50

 Eindruck

-0.50

 Gedanke

-0.50

 připo

-0.49

tonode

-0.49

 setempat

-0.49

 teorías

-0.49

POSITIVE LOGITS

(!)

0.46

(!)

0.45

 unbelievably

0.44

WritableDatabase

0.43

 fucking

0.42

rabbitmq

0.42

rofoam

0.42

ConstraintMaker

0.42

 incredibly

0.41

 elif

0.41

Activations Density 0.011%

intensifiers that emphasize the degree of the adjectives or adverbs in the text

intensifier followed by adjective or adverb

No Comments

No Known Activations