INDEX

Explanations

occurrences of the word "one."

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

preceding "one"

np_acts-logits-general · gemini-2.0-flash

referring to a single entity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

 Roskov

-0.60

TintMode

-0.56

 utafitiHapana

-0.55

URLException

-0.48

invokeLater

-0.48

GTCX

-0.47

exitRule

-0.46

:+:

-0.46

randomUUID

-0.44

bibfield

-0.44

POSITIVE LOGITS

 standing

0.45

 Standing

0.43

 coming

0.42

standing

0.41

ParallelGroup

0.41

LookAnd

0.40

STANDING

0.39

freunde

0.39

Standing

0.39

 belonging

0.38

Activations Density 0.210%

occurrences of the word "one."

preceding "one"

referring to a single entity

No Comments

No Known Activations