INDEX

Explanations

words and terms related to biological concepts and their interactions in various systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

-0.95

-0.78

anese

-0.75

enstein

-0.69

yethylene

-0.68

“

-0.68

hilfe

-0.67

-0.64

 yıld

-0.63

artments

-0.62

POSITIVE LOGITS

fore

1.15

 bezeichneter

1.15

ORE

1.12

 Mure

1.11

 Lore

1.06

 дописавши

1.05

 Nore

1.05

Ure

1.05

 Tare

1.04

verwijspagina

1.03

Activations Density 0.595%

words and terms related to biological concepts and their interactions in various systems

No Comments

No Known Activations