INDEX

Explanations

phrases indicating contrast or continuation

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate agreement or similarity in sentiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

]),

-0.81

arthed

-0.76

".[

-0.70

]).

-0.70

."[

-0.64

])

-0.63

).[

-0.62

è¦ļéĨĴ

-0.62

 respectively

-0.61

 âĨĳ

-0.60

POSITIVE LOGITS

elia

0.79

uh

0.73

unny

0.71

uin

0.70

 kidding

0.70

romeda

0.69

obin

0.68

 Courier

0.67

 funn

0.67

 yeah

0.66

Activations Density 0.310%

phrases indicating contrast or continuation

phrases that indicate agreement or similarity in sentiments

No Comments

No Known Activations