INDEX

Explanations

references to specific sections, figures, and citations in an academic context

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

SharedDtor

-0.87

findpost

-0.75

 Normdatei

-0.72

IntoConstraints

-0.70

djangoproject

-0.69

dflare

-0.67

 viewType

-0.66

 MenuView

-0.66

nologue

-0.66

 lenker

-0.64

POSITIVE LOGITS

 समीक्षाएं

0.47

lici

0.47

 noastră

0.45

 raport

0.44

Dax

0.43

sû

0.43

 surla

0.43

 deschis

0.43

">//

0.42

 देते

0.42

Activations Density 1.436%

references to specific sections, figures, and citations in an academic context

No Comments

No Known Activations