INDEX

Explanations

words related to roles and responsibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 энциклопедия

-0.66

ölker

-0.54

ertale

-0.52

клопе

-0.52

 nonatomic

-0.51

 Aner

-0.51

Udo

-0.51

OGN

-0.50

livan

-0.50

 midt

-0.50

POSITIVE LOGITS

 Therapeutic

0.68

Therapeutic

0.68

 Andy

0.64

 respectivamente

0.63

IsContent

0.63

cestry

0.61

Andy

0.60

 respectively

0.59

 therapeutic

0.59

 Therapeutics

0.59

Activations Density 0.117%

words related to roles and responsibilities

No Comments

No Known Activations