INDEX

Explanations

the presence of specific words related to violent events and actions

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

 soto

-0.63

 plis

-0.63

 ekos

-0.60

 muna

-0.59

 encre

-0.59

 stopp

-0.57

 cabrio

-0.57

 habang

-0.56

 Italijani

-0.56

 pecuni

-0.56

POSITIVE LOGITS

 écout

0.76

 fameux

0.65

 découv

0.61

 évit

0.61

 curieux

0.60

 parlant

0.59

 conçus

0.59

 offrant

0.58

 réal

0.58

 rassemb

0.58

Activations Density 0.337%

the presence of specific words related to violent events and actions

No Comments

No Known Activations