INDEX

Explanations

specific terminology related to scientific or legal concepts and evidence

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

before "for," "that," or "in"

np_acts-logits-general · gemini-2.0-flash

technical and abstract concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

züglich

-0.57

Referències

-0.51

AKER

-0.50

coni

-0.49

rified

-0.49

 Ανακτήθηκε

-0.48

chá

-0.48

lineHeight

-0.47

shadowRadius

-0.47

нето

-0.46

POSITIVE LOGITS

évaluateur

0.74

findpost

0.64

 TResult

0.60

存于互联网档案馆

0.60

RectangleBorder

0.60

 itſelf

0.60

 photolibrary

0.59

 ModelExpression

0.59

 Reſ

0.58

GOTREF

0.56

Activations Density 1.097%

specific terminology related to scientific or legal concepts and evidence

before "for," "that," or "in"

technical and abstract concepts

No Comments

No Known Activations