INDEX

Explanations

phrases related to investigating or discussing background information or details

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

 indestru

-0.61

 accla

-0.57

Vedi

-0.54

 inev

-0.54

Oltre

-0.52

 incarcer

-0.52

 depic

-0.51

 encomp

-0.50

 abstrait

-0.50

Abe

-0.49

POSITIVE LOGITS

 background

1.43

 Background

1.31

background

1.26

 backgrounds

1.25

Background

1.18

 BACKGROUND

1.11

BACKGROUND

1.04

背景

0.94

bg

0.92

bg

0.85

Activations Density 0.062%

phrases related to investigating or discussing background information or details

No Comments

No Known Activations