INDEX

Explanations

phrases related to issues of abuse and violence, specifically in the context of relationships and community dynamics

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

 honte

-0.65

 Diction

-0.55

 divisi

-0.54

 prét

-0.53

HTT

-0.53

 trouva

-0.53

 Kün

-0.53

 Continu

-0.50

 Sitemap

-0.50

 réjou

-0.49

POSITIVE LOGITS

(;;

0.61

 frustration

0.59

 frustrated

0.58

 frustrations

0.57

mistak

0.56

(;;)

0.55

 dissatisfied

0.53

relenting

0.52

 provocó

0.50

 bored

0.50

Activations Density 0.554%

phrases related to issues of abuse and violence, specifically in the context of relationships and community dynamics

No Comments

No Known Activations