INDEX

Explanations

terms related to engineering

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

 guma

-0.59

 kram

-0.58

 hina

-0.52

 katal

-0.51

 saha

-0.50

 karna

-0.49

 pardoned

-0.48

 kotor

-0.48

 Skor

-0.47

 simpel

-0.47

POSITIVE LOGITS

 engineering

1.30

 engineer

1.27

 Engineering

1.24

 engineers

1.23

Engineering

1.20

 Engineer

1.17

engineer

1.10

Engineer

1.10

 Engineers

1.10

engineering

1.09

Activations Density 0.061%

terms related to engineering

No Comments

No Known Activations