INDEX

Explanations

the word "is" with varying intensities in different contexts

oai_token-act-pair · gpt-3.5-turbo

statements asserting a truth or fact

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

throp

-0.79

stad

-0.76

rador

-0.73

assetsadobe

-0.69

eor

-0.66

andise

-0.65

inventoryQuantity

-0.65

chairs

-0.63

eatured

-0.62

allic

-0.62

POSITIVE LOGITS

 that

1.00

 THAT

0.85

 nobody

0.84

adays

0.76

 none

0.76

 simple

0.73

 there

0.73

 however

0.72

that

0.71

we

0.70

Activations Density 0.075%

the word "is" with varying intensities in different contexts

statements asserting a truth or fact

No Comments

No Known Activations