INDEX

Explanations

terms related to emotional responses and reactions

oai_token-act-pair · gpt-3.5-turbo

expressions of intensity or emotional weight in statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

pmwiki

-0.59

@#&

-0.57

yrics

-0.56

UFF

-0.56

istered

-0.56

inus

-0.53

pires

-0.52

pired

-0.51

 allegedly

-0.50

ilian

-0.50

POSITIVE LOGITS

 someday

1.41

 tomorrow

1.17

 anytime

1.08

 hereafter

0.91

 sooner

0.84

 next

0.81

 soon

0.80

 sometime

0.79

 future

0.76

morrow

0.74

Activations Density 1.488%

terms related to emotional responses and reactions

expressions of intensity or emotional weight in statements

No Comments

No Known Activations