INDEX

Explanations

words related to crime and law, especially regarding theft and coercion

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

WithIOException

-0.61

 malheureux

-0.61

 couteau

-0.61

 oiseau

-0.59

 vainqueur

-0.58

 oeil

-0.58

 monstre

-0.58

 vété

-0.56

 minY

-0.55

 doigt

-0.54

POSITIVE LOGITS

Fitment

0.63

MOQ

0.61

 entire

0.60

 underlying

0.57

 same

0.56

 destina

0.56

/**

0.55

 respective

0.55

 palet

0.54

/*

0.53

Activations Density 0.518%

words related to crime and law, especially regarding theft and coercion

No Comments

No Known Activations