INDEX

Explanations

technology-related terms, such as software names and programming languages

oai_token-act-pair · gpt-3.5-turbo

technical terms related to software and technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

famous

-0.60

ournals

-0.59

usra

-0.57

owitz

-0.57

olina

-0.56

oples

-0.55

 "$:/

-0.54

ocamp

-0.54

ĸļ

-0.53

ukemia

-0.53

POSITIVE LOGITS

 agility

0.59

 handling

0.58

ĨĴ

0.55

 combustion

0.53

 upgr

0.53

Applic

0.53

 faculties

0.52

GY

0.52

 assist

0.51

deg

0.50

Activations Density 1.165%

technology-related terms, such as software names and programming languages

technical terms related to software and technology

No Comments

No Known Activations