INDEX

Explanations

phrases indicating emphasis or importance

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

 parch

-1.21

 affor

-1.16

 maneu

-1.15

 milf

-1.15

 intermitt

-1.14

 inext

-1.14

 ?...

-1.11

 increa

-1.11

 excru

-1.10

 ardu

-1.09

POSITIVE LOGITS

Eso

0.61

why

0.61

 VIDEOTAPE

0.60

Ngoài

0.55

 happening

0.52

Poppins

0.51

Charakter

0.50

첫

0.50

why

0.49

Gambas

0.49

Activations Density 0.277%

phrases indicating emphasis or importance

No Comments

No Known Activations