INDEX

Explanations

terms related to scientific research and medical studies

oai_token-act-pair · gpt-3.5-turbo

the presence of the phrase "in" followed by various contexts related to biological or medical processes

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

INESS

-0.72

Const

-0.70

llor

-0.68

LOD

-0.67

iHUD

-0.66

 guessed

-0.66

sbm

-0.66

é¾įå¥ĳå£«

-0.66

own

-0.65

Offic

-0.65

POSITIVE LOGITS

 vitro

1.72

 vivo

1.59

 situ

1.39

activation

1.36

 rodents

1.29

 humans

1.25

 mice

1.22

 mammals

1.20

 primates

1.18

ulin

1.15

Activations Density 0.149%

terms related to scientific research and medical studies

the presence of the phrase "in" followed by various contexts related to biological or medical processes

No Comments

No Known Activations