INDEX

Explanations

words related to computer programming, security, and technology

oai_token-act-pair · gpt-3.5-turbo

terms related to coding or programming languages

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

 Arabian

-0.67

 Borders

-0.65

Dos

-0.65

Sea

-0.64

Mek

-0.64

 Richards

-0.63

 Nicarag

-0.63

 lull

-0.63

 Norris

-0.63

Ell

-0.62

POSITIVE LOGITS

based

1.35

specific

1.21

sized

1.20

derived

1.17

level

1.16

related

1.15

type

1.13

driven

1.13

centric

1.13

wise

1.12

Activations Density 0.138%

words related to computer programming, security, and technology

terms related to coding or programming languages

No Comments

No Known Activations