INDEX

Explanations

phrases indicating a comparison or contrast

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

oslov

-0.77

ww

-0.76

oud

-0.75

SPONSORED

-0.69

::::::::

-0.68

kaya

-0.67

$.

-0.66

Í

-0.63

nee

-0.62

kay

-0.61

POSITIVE LOGITS

 discussing

1.41

 assessing

1.36

 deciding

1.34

 evaluating

1.33

 confronted

1.32

 determining

1.31

 dealing

1.30

 comparing

1.25

 faced

1.22

 describing

1.19

Activations Density 0.086%

phrases indicating a comparison or contrast

No Comments

No Known Activations