INDEX

Explanations

phrases indicating doubt or uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

uvwxyz

-0.60

 quoque

-0.55

今度は

-0.52

 chi̍t

-0.52

 tambi

-0.50

 tuli

-0.50

 alternately

-0.49

 strtolower

-0.49

argest

-0.48

 moſt

-0.48

POSITIVE LOGITS

 transfieras

0.93

IntoConstraints

0.91

 ProtoMessage

0.87

 jScrollPane

0.83

AutoresizingMask

0.78

 NSCoder

0.77

GraphicsUnit

0.77

MigrationBuilder

0.75

awtextra

0.72

 nenhuma

0.70

Activations Density 0.596%

phrases indicating doubt or uncertainty

No Comments

No Known Activations