INDEX

Explanations

phrases indicating potential impact or consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

blico

-0.48

lå

-0.47

 istället

-0.46

 ogóle

-0.45

 stesse

-0.45

 bajos

-0.45

VIAF

-0.45

 altos

-0.45

 estimés

-0.43

 jsPsych

-0.43

POSITIVE LOGITS

Datuak

0.71

reportWebVitals

0.67

 الدولى

0.64

userdetails

0.62

 MainAxisSize

0.62

ChildScrollView

0.59

Portale

0.59

 Nhưng

0.59

ίναι

0.57

TintMode

0.57

Activations Density 0.345%

phrases indicating potential impact or consequences

No Comments

No Known Activations