INDEX

Explanations

references to body parts and personal pronouns

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

gänger

-0.50

amoan

-0.47

schmidt

-0.47

iterraneo

-0.45

batore

-0.45

Cor

-0.44

Det

-0.43

Bu

-0.43

Pet

-0.43

Rut

-0.43

POSITIVE LOGITS

 StatelessWidget

0.73

tvguidetime

0.72

 فريبيس

0.72

MemoryWarning

0.69

 BoxDecoration

0.67

Personendaten

0.66

AndEndTag

0.66

ReusableCell

0.65

 שוליים

0.63

 cherries

0.63

Activations Density 0.331%

references to body parts and personal pronouns

No Known Activations