INDEX

Explanations

phrases related to assumptions and assumptions being made

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

phrases indicating assumptions or beliefs

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

making assumptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 venons

-0.53

vent

-0.52

Millisecond

-0.51

PCell

-0.51

リエステル

-0.50

 Pingback

-0.49

 Audiodateien

-0.49

tır

-0.49

retch

-0.49

oughlin

-0.49

POSITIVE LOGITS

 Assumptions

0.81

Personensuche

0.78

WebElementEntity

0.76

 ProtoMessage

0.74

textAppearance

0.72

près

0.70

RegistryLite

0.70

الإنجليزية

0.69

neurial

0.69

 correctes

0.68

Activations Density 0.052%

phrases related to assumptions and assumptions being made

phrases indicating assumptions or beliefs

making assumptions

No Comments

No Known Activations