INDEX

Explanations

numbers, items on a list, and related information in structured formats like time or location

oai_token-act-pair · gpt-3.5-turbo

time and date-related information

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 shedding

-0.53

 surrog

-0.53

 assum

-0.53

 overl

-0.53

 infl

-0.52

 redund

-0.52

 toget

-0.52

 narrowing

-0.51

 undermin

-0.51

 destro

-0.51

POSITIVE LOGITS

 âĵĺ

0.90

 Location

0.70

 Joined

0.67

;;;;;;;;;;;;

0.66

 Profile

0.64

 à¨

0.64

Apr

0.63

0.62

 ãĥ

0.62

0.61

Activations Density 0.627%

numbers, items on a list, and related information in structured formats like time or location

time and date-related information

No Comments

No Known Activations