INDEX

Explanations

locations or proper nouns related to different countries

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

<bos>

-0.66

உ

-0.61

Horário

-0.58

ஒ

-0.57

 trattano

-0.55

Parabéns

-0.55

Доброго

-0.55

 Walkover

-0.54

Hör

-0.54

Schweizer

-0.53

POSITIVE LOGITS

 unwarran

1.39

 unspeak

1.31

 disagre

1.30

 McLaugh

1.25

 gaily

1.24

 excru

1.20

 apprehen

1.18

 pamph

1.18

 impra

1.17

 inappro

1.16

Activations Density 0.357%

locations or proper nouns related to different countries

No Comments

No Known Activations