INDEX

Explanations

phrases indicating lists or examples

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

KommentareTeilen

-0.64

OGND

-0.57

 lainnya

-0.57

 оригіналу

-0.57

地看着

-0.55

rdı

-0.55

rboles

-0.55

contentLoaded

-0.53

tymologie

-0.53

Geplaatst

-0.53

POSITIVE LOGITS

 following

3.76

following

3.29

 Following

2.78

 FOLLOWING

2.71

Following

2.69

 siguientes

2.46

 seguenti

2.39

 seguinte

2.37

 siguiente

2.30

 seguintes

2.23

Activations Density 0.934%

phrases indicating lists or examples

No Comments

No Known Activations