INDEX

Explanations

phrases that express uncertainty or seek guidance on a change in circumstances

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

Personendaten

-0.90

цездатний

-0.84

Попис

-0.82

 мәкал

-0.79

 betweenstory

-0.78

SourceChecksum

-0.77

rungsseite

-0.75

 AspNetCore

-0.75

 pleaſure

-0.74

 Taktlose

-0.74

POSITIVE LOGITS

手段

0.43

 counter

0.42

ANTY

0.42

viewDidLoad

0.40

topus

0.40

 cesta

0.40

只能

0.39

Grá

0.39

ძ

0.39

fxml

0.38

Activations Density 0.200%

phrases that express uncertainty or seek guidance on a change in circumstances

No Comments

No Known Activations