INDEX

Explanations

phrases related to proving a point or showcasing accomplishments

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

 teras

-0.68

はじめに

-0.62

ert

-0.59

NKC

-0.58

 kram

-0.57

Okt

-0.56

 kaka

-0.55

 kano

-0.55

miy

-0.54

 lele

-0.54

POSITIVE LOGITS

 prove

1.07

 disprove

1.03

 proves

0.93

 proving

0.91

 proved

0.86

 Prove

0.80

 proof

0.80

prove

0.76

 defy

0.76

 defied

0.75

Activations Density 0.375%

phrases related to proving a point or showcasing accomplishments

No Comments

No Known Activations