INDEX

Explanations

the presence of technical terms or jargon related to websites, search results, and user experience

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

 Coim

-0.92

 McLaugh

-0.91

 Vaugh

-0.91

 Augu

-0.85

 Penna

-0.80

 McInt

-0.80

 Thos

-0.79

Juf

-0.77

 Rine

-0.76

 Bartholo

-0.76

POSITIVE LOGITS

<bos>

1.25

 reading

0.77

 read

0.75

reading

0.71

 READING

0.68

read

0.67

 digest

0.65

 reads

0.57

reader

0.57

 READ

0.56

Activations Density 0.538%

the presence of technical terms or jargon related to websites, search results, and user experience

No Comments

No Known Activations