INDEX

Explanations

traits or behaviors that might be considered negative or off-putting in social situations

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

 congrès

-0.68

 Occidente

-0.67

 Când

-0.67

Ră

-0.65

 Ibidem

-0.65

 villaggio

-0.64

 Rumania

-0.62

 dénon

-0.62

 Alcalde

-0.62

 Rois

-0.61

POSITIVE LOGITS

 bother

0.66

 anything

0.66

 anymore

0.63

 necessarily

0.63

anything

0.59

<bos>

0.59

any

0.59

 bothered

0.58

 worry

0.56

 affect

0.55

Activations Density 0.443%

traits or behaviors that might be considered negative or off-putting in social situations

No Comments

No Known Activations