INDEX

Explanations

details related to product safety instructions and warnings

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

 détaillé

-0.49

Hii

-0.49

 intéressante

-0.49

FlatStyle

-0.48

 inconnu

-0.47

.*")]

-0.47

 récente

-0.46

ulihan

-0.46

 woll

-0.46

dients

-0.45

POSITIVE LOGITS

 🤣🤣

0.65

 tupperware

0.64

 cushi

0.62

IsContent

0.57

 🥲

0.57

 🔥🔥

0.56

 tutt

0.55

Fuckin

0.55

 Più

0.55

vece

0.53

Activations Density 0.386%

details related to product safety instructions and warnings

No Comments

No Known Activations