INDEX

Explanations

words related to viruses and vaccinations

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

 volunte

-0.87

 Keny

-0.87

Juf

-0.87

 thut

-0.86

 Augu

-0.85

 fortn

-0.84

 lele

-0.82

 McLaugh

-0.82

 purcha

-0.82

 encomp

-0.81

POSITIVE LOGITS

greja

0.63

 BIBSYS

0.63

ValueStyle

0.60

 '\\;'

0.57

πάρχ

0.56

 pinulongan

0.55

xodo

0.54

NKC

0.53

ELDS

0.53

 gelt

0.53

Activations Density 0.459%

words related to viruses and vaccinations

No Comments

No Known Activations