INDEX

Explanations

proper nouns and names throughout the text

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

personal names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kasarigan

-0.65

ValueStyle

-0.61

:✨

-0.58

Autoritní

-0.55

bootstrapcdn

-0.53

OGND

-0.52

IFICATE

-0.52

arina

-0.50

uxxxx

-0.50

ipients

-0.50

POSITIVE LOGITS

ędziesz

0.37

 himself

0.35

 zufolge

0.35

’

0.34

 will

0.32

 getroffen

0.31

who

0.31

 RSSSF

0.31

 chofe

0.31

Activations Density 0.026%

proper nouns and names throughout the text

personal names

No Comments

No Known Activations