INDEX

Explanations

proper nouns related to a specific name 'Wilbur'

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring "bur" within words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

uncture

-0.83

 SYSTEM

-0.74

 partName

-0.70

 Spac

-0.69

 Dangerous

-0.68

 Controlled

-0.67

perture

-0.66

 Tune

-0.62

 Scand

-0.61

 Logged

-0.60

POSITIVE LOGITS

querque

1.25

ger

1.12

idays

1.01

rowing

0.98

ging

0.94

rito

0.94

rows

0.93

geoning

0.92

sts

0.91

thur

0.90

Activations Density 0.006%

proper nouns related to a specific name 'Wilbur'

occurrences of the substring "bur" within words

No Comments

No Known Activations