INDEX

Explanations

prepositional phrases starting with 'of a'

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

 Bettina

-0.74

 Illus

-0.71

EEU

-0.69

 berea

-0.66

miu

-0.66

 Tanja

-0.66

Edy

-0.66

 cuban

-0.63

 Ines

-0.62

 shenan

-0.62

POSITIVE LOGITS

<bos>

1.11

 kapag

0.63

ształ

0.63

 kasama

0.59

 itong

0.58

 kabel

0.58

 siyang

0.56

 habang

0.56

 meil

0.55

 kahit

0.55

Activations Density 0.152%

prepositional phrases starting with 'of a'

No Comments

No Known Activations