INDEX

Explanations

mentions of specific people or entities in a comparative context

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate references or comparisons involving "the likes of" someone or something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

rang

-0.71

é¾įå¥ĳå£«

-0.70

 teasp

-0.69

ħĭ

-0.67

Ô

-0.67

 proport

-0.67

INAL

-0.67

 conduc

-0.66

IAL

-0.65

ĸļ

-0.64

POSITIVE LOGITS

 ours

0.80

 Rodriguez

0.70

 those

0.68

 Phillips

0.67

 Neal

0.66

Rut

0.66

 Julius

0.66

 Henry

0.66

 Franklin

0.65

 Machina

0.65

Activations Density 0.060%

mentions of specific people or entities in a comparative context

phrases that indicate references or comparisons involving "the likes of" someone or something

No Comments

No Known Activations