INDEX

Explanations

phrases related to the quantity or degree of something

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

 shenan

-1.69

 reluct

-1.65

 depic

-1.63

 emphat

-1.55

 affor

-1.51

 increa

-1.50

 unspeak

-1.48

 disagre

-1.48

 inconce

-1.46

 intersper

-1.46

POSITIVE LOGITS

too

0.85

too

0.78

Too

0.77

Too

0.76

TOO

0.73

 demasiado

0.66

TOO

0.66

 quá

0.65

 calendriers

0.65

<bos>

0.59

Activations Density 0.304%

phrases related to the quantity or degree of something

No Comments

No Known Activations