INDEX

Explanations

adjectives expressing positive or negative opinions about various aspects of something

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 silikon

-1.30

 kön

-1.22

 keramik

-1.22

 optik

-1.21

 mikrofon

-1.20

 alkoh

-1.19

 kafe

-1.14

 kosme

-1.13

 panik

-1.13

 maksi

-1.12

POSITIVE LOGITS

Cześć

0.91

muito

0.89

Witaj

0.87

 quite

0.76

 Muito

0.76

Nichts

0.75

Bardzo

0.75

 intersper

0.73

 pretty

0.72

 imageName

0.72

Activations Density 0.438%

adjectives expressing positive or negative opinions about various aspects of something

No Comments

No Known Activations