INDEX

Explanations

references to figures and visual data representations in the text

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

eload

-0.46

VST

-0.46

Ea

-0.44

cheon

-0.42

lop

-0.42

sb

-0.42

Sb

-0.41

ming

-0.41

ALF

-0.40

HIL

-0.40

POSITIVE LOGITS

 snippetHide

0.66

 disponibilités

0.59

FIGURE

0.55

 المعيارى

0.55

figcaption

0.50

__(/*!

0.48

 nonatomic

0.48

minipage

0.48

Rüyada

0.47

Bronnen

0.47

Activations Density 0.380%

references to figures and visual data representations in the text

No Known Activations