INDEX

Explanations

mentions of terms related to veterans, their status, and organizations involved with veterans

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

 fortn

-0.97

 effe

-0.96

 seiz

-0.91

 volunte

-0.90

 laun

-0.88

 strick

-0.85

 inder

-0.85

 wien

-0.84

 calvin

-0.84

 carc

-0.83

POSITIVE LOGITS

 veterans

1.22

 veteran

1.17

 Veterans

1.09

 Veteran

1.06

Veterans

1.01

veter

1.01

Veteran

0.96

vet

0.93

 VETER

0.92

 vets

0.79

Activations Density 0.066%

mentions of terms related to veterans, their status, and organizations involved with veterans

No Comments

No Known Activations