INDEX

Explanations

phrases related to potential dangers, risks, and catastrophic events

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

 thut

-1.93

aen

-1.93

 effe

-1.93

 nece

-1.85

fte

-1.84

fta

-1.82

 „,

-1.81

 ?...

-1.76

fep

-1.76

 meis

-1.76

POSITIVE LOGITS

if

0.80

due

0.72

or

0.67

0.66

 unless

0.66

if

0.65

 because

0.63

<bos>

0.63

roasted

0.63

due

0.62

Activations Density 0.508%

phrases related to potential dangers, risks, and catastrophic events

No Comments

No Known Activations