INDEX

Explanations

phrases related to questioning or highlighting specific issues for further examination

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

 klap

-0.97

 peculi

-0.94

 spion

-0.94

 stoff

-0.92

 ordina

-0.92

 plak

-0.90

 solidar

-0.89

 simplif

-0.88

 profi

-0.86

hek

-0.84

POSITIVE LOGITS

raught

0.62

 sobald

0.59

 syndrome

0.57

bigsqcup

0.56

andaş

0.54

AfterClass

0.53

messageInfo

0.53

(['/

0.52

findViewById

0.51

addField

0.49

Activations Density 0.641%

phrases related to questioning or highlighting specific issues for further examination

No Comments

No Known Activations