INDEX

Explanations

references to a specific word or character sequence, "Ro zz"

oai_token-act-pair · gpt-3.5-turbo

instances of the name "Ro z z" and variations of it

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

 Polar

-0.71

 lapse

-0.68

vict

-0.68

 Conrad

-0.68

 foremost

-0.67

 Scots

-0.67

 fitness

-0.66

 appropriation

-0.65

 conditioning

-0.64

¥µ

-0.62

POSITIVE LOGITS

zz

1.23

arella

1.12

ucc

0.97

ZZ

0.95

arro

0.95

olla

0.94

hou

0.93

Feed

0.92

azz

0.90

edd

0.90

Activations Density 0.017%

references to a specific word or character sequence, "Ro zz"

instances of the name "Ro z z" and variations of it

No Comments

No Known Activations