INDEX

Explanations

phrases indicating a location and its attributes

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the existence or presence of 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

chuk

-0.68

 destro

-0.67

AMI

-0.62

ãĥ¼ãĥĨ

-0.61

itaire

-0.59

Intern

-0.59

emale

-0.59

awa

-0.58

sylv

-0.57

é¾įå

-0.55

POSITIVE LOGITS

 largeDownload

0.58

bra

0.55

ye

0.52

actionDate

0.50

 Baltimore

0.49

 Abbas

0.49

 Palestinians

0.48

 Image

0.47

 Entered

0.47

 unders

0.47

Activations Density 0.566%

phrases indicating a location and its attributes

phrases indicating the existence or presence of something

No Comments

No Known Activations