INDEX

Explanations

phrases related to knowledge or stating facts

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

 optik

-0.69

 kapital

-0.63

 kristal

-0.60

 silikon

-0.60

 adal

-0.60

 etik

-0.58

 keramik

-0.58

 ekster

-0.56

 kilomet

-0.55

 alkoh

-0.55

POSITIVE LOGITS

 disreg

0.89

 know

0.81

 shenan

0.80

 unspeak

0.80

know

0.78

 KNOW

0.76

 knows

0.72

 quivering

0.71

 impra

0.70

 Know

0.69

Activations Density 0.074%

phrases related to knowledge or stating facts

No Comments

No Known Activations