INDEX

Explanations

measurements in kilometers and miles

oai_token-act-pair · gpt-3.5-turbo

numerical values associated with distances or measurements

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

ãĤ¢ãĥ«

-0.64

ãĥĦ

-0.64

tnc

-0.63

ãĥ¥

-0.62

Reviewer

-0.61

 answ

-0.60

(&

-0.60

soDeliveryDate

-0.59

¾

-0.58

tags

-0.57

POSITIVE LOGITS

 apiece

0.77

ãĥİ

0.69

 respectively

0.68

 reserved

0.66

yards

0.63

eous

0.61

ridges

0.61

oused

0.61

+.

0.60

 devoted

0.56

Activations Density 0.071%

measurements in kilometers and miles

numerical values associated with distances or measurements

No Comments

No Known Activations