INDEX

Explanations

information related to opinions about different aspects of media and expressions of strong opinions

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

 akut

-1.03

 antik

-1.01

 vasi

-1.00

 maksi

-1.00

 meras

-0.97

 bakteri

-0.96

 ekos

-0.93

 makro

-0.92

 optik

-0.90

 teras

-0.89

POSITIVE LOGITS

 indestru

1.17

 impra

1.05

 intersper

0.99

 unspeak

0.96

 shenan

0.96

pozdrawiam

0.93

 disagre

0.92

 cushi

0.90

 pamph

0.90

 reluct

0.90

Activations Density 0.255%

information related to opinions about different aspects of media and expressions of strong opinions

No Comments

No Known Activations