INDEX

Explanations

Special characters related to text formatting

oai_token-act-pair · gpt-3.5-turbo

a specific character or sequence of symbols that may indicate confusion or distress in communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 guiActiveUnfocused

-0.92

 Droid

-0.65

 Morse

-0.64

 Ballistic

-0.63

 ballistic

-0.63

 Golem

-0.63

RAD

-0.63

anwhile

-0.61

Yad

-0.61

 Gadget

-0.61

POSITIVE LOGITS

should

1.00

Ĵ

0.86

Â¢

0.85

say

0.83

could

0.83

certain

0.82

âĢķ

0.79

ume

0.79

¥

0.78

pires

0.78

Activations Density 0.222%

Special characters related to text formatting

a specific character or sequence of symbols that may indicate confusion or distress in communication

No Comments

No Known Activations