INDEX

Explanations

examples or instances

oai_token-act-pair · gpt-3.5-turbo

phrases that introduce examples or illustrative cases

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

 Rodham

-0.78

 Mehran

-0.68

psey

-0.61

 Guant

-0.59

"—

-0.59

\.

-0.58

 ÂŃ

-0.56

Ö

-0.55

assador

-0.55

],"

-0.54

POSITIVE LOGITS

Example

0.79

 drawback

0.79

 Example

0.75

 Examples

0.73

cknowled

0.72

 downside

0.70

oret

0.68

 disadvantages

0.68

Additionally

0.67

 example

0.66

Activations Density 0.728%

examples or instances

phrases that introduce examples or illustrative cases

No Comments

No Known Activations