INDEX

Explanations

mentions of specific political and governmental terms and concepts

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

 delà

-0.66

ATEGORY

-0.64

paravant

-0.63

 fince

-0.63

 insuffisamment

-0.61

 leaft

-0.59

 whofe

-0.59

 "..\..\..\

-0.59

esterday

-0.58

 follic

-0.58

POSITIVE LOGITS

 successor

0.64

 newList

0.56

 newName

0.55

new

0.54

 unified

0.53

 someday

0.53

 revamped

0.52

 newData

0.52

 semblables

0.52

 comprehensive

0.52

Activations Density 0.456%

mentions of specific political and governmental terms and concepts

No Comments

No Known Activations