INDEX

Explanations

numerical expressions representing time duration

oai_token-act-pair · gpt-3.5-turbo

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

rower

-0.62

soever

-0.61

 Dare

-0.60

 boldly

-0.60

 dearly

-0.58

isen

-0.58

 Operator

-0.58

icultural

-0.57

grave

-0.57

dale

-0.57

POSITIVE LOGITS

%"

1.26

 dozen

1.23

dozen

1.18

 minutes

0.98

 percent

0.97

%.

0.93

 cents

0.93

 miles

0.92

%:

0.90

Activations Density 0.119%

numerical expressions representing time duration

No Comments

No Known Activations