INDEX

Explanations

phrases emphasizing relationships and connections between individuals or groups

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itſelf

-1.13

 ſtate

-1.02

 themſelves

-0.99

 pleaſure

-0.98

 Jefus

-0.97

 myſelf

-0.97

ſelf

-0.96

 Majefty

-0.92

 occaf

-0.92

Efq

-0.90

POSITIVE LOGITS

two

1.10

two

1.09

Two

1.05

Two

1.01

TWO

1.00

TWO

1.00

 שני

0.95

 zwei

0.95

 deux

0.89

 δύο

0.89

Activations Density 0.086%

phrases emphasizing relationships and connections between individuals or groups

No Comments

No Known Activations