INDEX

Explanations

keywords related to computer programming tasks and methods, especially involving debugging and code optimization

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

 utop

-0.79

 solidar

-0.71

 notor

-0.67

 sement

-0.60

 prostitu

-0.60

 intrig

-0.58

trás

-0.58

 ideolog

-0.58

 psychiat

-0.58

 gesta

-0.57

POSITIVE LOGITS

 indestru

0.65

ówczas

0.59

 then

0.58

 Whence

0.56

 motherfucker

0.55

 dragonfly

0.55

 rascal

0.54

 disreg

0.53

Sklici

0.53

 tawny

0.53

Activations Density 0.371%

keywords related to computer programming tasks and methods, especially involving debugging and code optimization

No Comments

No Known Activations