INDEX

Explanations

mentions of DNA, forensic information, and medical evidence

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

 caballeros

-0.47

 Batalla

-0.47

 externi

-0.47

 Krise

-0.47

 ronda

-0.46

 bestia

-0.45

**/

-0.44

 Provinces

-0.42

 Province

-0.41

 moedas

-0.41

POSITIVE LOGITS

DNA

1.29

DNA

1.25

dna

1.04

 îna

0.81

dna

0.81

 coö

0.76

 disagre

0.75

 ajuns

0.74

 împre

0.74

 increa

0.70

Activations Density 0.057%

mentions of DNA, forensic information, and medical evidence

No Comments

No Known Activations