INDEX

Explanations

specific times or durations mentioned in a document

oai_token-act-pair · gpt-3.5-turbo

numerical representations of time and duration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

dale

-0.72

bra

-0.72

abee

-0.66

stained

-0.62

 dearly

-0.62

landers

-0.60

thood

-0.59

geon

-0.59

wered

-0.58

lights

-0.58

POSITIVE LOGITS

 dozen

0.87

 thous

0.86

OTAL

0.76

dozen

0.76

 percent

0.75

 hours

0.70

 thirds

0.70

%"

0.68

 thousand

0.67

 cents

0.64

Activations Density 0.168%

specific times or durations mentioned in a document

numerical representations of time and duration

No Comments

No Known Activations