INDEX

Explanations

statements related to military operations or political actions

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

 increa

-1.76

 emphat

-1.70

 strick

-1.68

 erad

-1.67

 encomp

-1.66

 disagre

-1.64

 inev

-1.63

 intersper

-1.62

 depic

-1.62

 maneu

-1.61

POSITIVE LOGITS

 therefore

1.01

 hence

0.91

therefore

0.81

Therefore

0.80

 thus

0.80

 Therefore

0.78

 accordingly

0.74

 consequently

0.74

hence

0.72

 decided

0.71

Activations Density 0.521%

statements related to military operations or political actions

No Comments

No Known Activations