INDEX

Explanations

phrases indicating uncertainty or comparison between multiple elements

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

 tré

-0.58

 trá

-0.55

 sér

-0.54

<s>

-0.54

 sexu

-0.53

 Horizonte

-0.53

 Wikimédia

-0.52

EOR

-0.52

urie

-0.49

vains

-0.49

POSITIVE LOGITS

 unspeak

1.35

 indestru

1.34

 shenan

1.28

 reluct

1.27

 unwarran

1.26

 disagre

1.25

 unlaw

1.20

 uninten

1.20

ftu

1.17

 impra

1.16

Activations Density 2.163%

phrases indicating uncertainty or comparison between multiple elements

No Comments

No Known Activations