INDEX

Explanations

references to specific events or quotes

oai_token-act-pair · gpt-3.5-turbo

expressions of pain or discomfort related to emotional experiences

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 unsurprisingly

-0.62

 moreover

-0.57

 similarly

-0.57

surprisingly

-0.56

anwhile

-0.54

 predictably

-0.54

 additionally

-0.52

 meanwhile

-0.51

 reportedly

-0.50

 furthermore

-0.50

POSITIVE LOGITS

 âĢ¦"

0.93

âĢ¦"

0.90

..."

0.86

âĢ¦."

0.82

 ..."

0.81

 fuckin

0.73

 gonna

0.70

-"

0.70

?"

0.67

?'

0.66

Activations Density 1.484%

references to specific events or quotes

expressions of pain or discomfort related to emotional experiences

No Comments

No Known Activations