INDEX

Explanations

phrases related to prior conditions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pleaſure

-0.86

 AssemblyTitle

-0.85

 habet

-0.75

 Jefus

-0.74

ſelf

-0.72

 fometimes

-0.71

 itſelf

-0.71

 pleaf

-0.70

ítě

-0.68

 reafon

-0.68

POSITIVE LOGITS

 before

2.16

before

2.06

 Before

1.97

Before

1.91

BEFORE

1.85

 BEFORE

1.77

 sebelum

1.73

 antes

1.66

 πριν

1.57

 innan

1.53

Activations Density 0.143%

phrases related to prior conditions or events

No Comments

No Known Activations