INDEX

Explanations

mentions of military-related terms and historical events

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

 ?...

-0.54

 manik

-0.54

 encomp

-0.54

 !...

-0.53

 ciasc

-0.52

 logarith

-0.52

 depic

-0.51

 amanda

-0.50

adona

-0.50

 perchance

-0.50

POSITIVE LOGITS

 General

1.09

General

1.06

general

1.05

 GENERAL

1.02

 general

1.01

GENERAL

0.99

eneral

0.93

Général

0.87

 Geral

0.87

 général

0.84

Activations Density 0.071%

mentions of military-related terms and historical events

No Comments

No Known Activations