INDEX

Explanations

phrases related to changes or transitions

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eful

-0.74

acea

-0.67

LOCK

-0.67

arest

-0.66

etary

-0.64

ounding

-0.64

iar

-0.62

 unanswered

-0.58

bey

-0.58

hest

-0.58

POSITIVE LOGITS

now

1.10

 lately

1.07

 nowadays

1.07

 recently

0.97

 suddenly

0.95

 gradually

0.90

 morphed

0.87

now

0.87

 changed

0.86

uddenly

0.83

Activations Density 0.371%

phrases related to changes or transitions

No Comments

No Known Activations