INDEX

Explanations

phrases where the word 'the' is followed by a numerical value

oai_token-act-pair · gpt-3.5-turbo

the definite article "the" 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 respectively

-0.75

 whenever

-0.74

 instead

-0.72

rather

-0.68

 followed

-0.67

 shortly

-0.65

 both

-0.64

watch

-0.64

 whilst

-0.63

 Finally

-0.62

POSITIVE LOGITS

 slightest

1.75

 anymore

1.32

nor

1.21

 specifics

1.16

 usual

1.09

 actual

0.99

 merits

0.93

 foreseeable

0.90

 particulars

0.89

 entirety

0.88

Activations Density 0.416%

phrases where the word 'the' is followed by a numerical value

the definite article "the" in various contexts

No Comments

No Known Activations