INDEX

Explanations

the modal verb "would" followed by a verb in past tense

oai_token-act-pair · gpt-3.5-turbo

the use of the letter 'd' in various contexts

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

 tensions

-0.66

Nun

-0.62

 tension

-0.61

 Remem

-0.60

 Lambert

-0.56

Kos

-0.56

 Tayyip

-0.56

Sut

-0.55

 waivers

-0.55

 organisers

-0.54

POSITIVE LOGITS

ividual

1.26

iamond

1.03

iversity

0.97

hyde

0.94

orf

0.93

rown

0.93

gins

0.93

ynasty

0.91

onna

0.90

ynam

0.90

Activations Density 0.020%

the modal verb "would" followed by a verb in past tense

the use of the letter 'd' in various contexts

No Comments

No Known Activations