INDEX

Explanations

mentions about experiences, skills, and education, emphasizing experience-related 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

 increa

-1.52

 lidl

-1.44

 stockholm

-1.39

 wherea

-1.38

 effe

-1.38

 thut

-1.36

 coö

-1.35

aen

-1.35

 inev

-1.34

 encomp

-1.34

POSITIVE LOGITS

 experience

0.99

experience

0.83

 expertise

0.80

 proven

0.78

Experience

0.75

 Experience

0.74

 experiences

0.71

 experienced

0.70

 familiarity

0.70

 prior

0.68

Activations Density 0.448%

mentions about experiences, skills, and education, emphasizing experience-related details

No Comments

No Known Activations