INDEX

Explanations

refer to historical and geographical terms and locations, specifically discussing advancements and industries in the past

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 affez

-1.22

 Ottobre

-1.18

 robus

-1.14

 ordina

-1.11

 parteci

-1.08

 sappi

-1.07

 solidar

-1.06

TagMode

-1.06

 vogli

-1.04

 LIRE

-1.04

POSITIVE LOGITS

 ineffec

1.26

 unavoid

1.11

 impelled

1.08

 unspeak

1.08

 McLaugh

1.05

 Vaugh

1.03

 shenan

1.02

 McInt

1.00

 sophistic

0.99

 impra

0.98

Activations Density 4.430%

refer to historical and geographical terms and locations, specifically discussing advancements and industries in the past

No Comments

No Known Activations