INDEX

Explanations

locations or places

oai_token-act-pair · gpt-3.5-turbo

locations and places mentioned in the text

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

 positives

-0.52

 omission

-0.49

adv

-0.48

=/

-0.47

 wearer

-0.47

 subscript

-0.47

ãģĦ

-0.46

 bearer

-0.45

 downgrade

-0.45

 contr

-0.45

POSITIVE LOGITS

 Township

0.74

 Peninsula

0.71

 Junction

0.71

 Gardens

0.70

 Harbor

0.69

 Meadows

0.69

 Heights

0.69

 Village

0.68

opolis

0.68

 District

0.67

Activations Density 0.572%

locations or places

locations and places mentioned in the text

No Comments

No Known Activations