INDEX

Explanations

email-related phrases or references

oai_token-act-pair · gpt-3.5-turbo

the letter 'e' in various contexts within text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Anthem

-0.70

 Kitchen

-0.70

NEC

-0.67

 Operator

-0.62

 Katz

-0.61

 Kats

-0.61

 Petty

-0.60

ãĤ¤ãĥĪ

-0.60

 Vulkan

-0.59

 Burton

-0.59

POSITIVE LOGITS

tymology

1.38

gypt

1.27

agles

1.24

ighth

1.22

arthed

1.22

ternally

1.21

ugen

1.15

thereum

1.12

lements

1.07

pee

1.03

Activations Density 0.038%

email-related phrases or references

the letter 'e' in various contexts within text

No Comments

No Known Activations