INDEX

Explanations

phrases indicating contrasting or differing opinions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating contrasting opinions or evaluations

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

ĸļ

-0.78

andise

-0.75

INS

-0.66

gross

-0.66

Attach

-0.61

Constructed

-0.60

ucc

-0.60

 subscribing

-0.60

ensor

-0.60

ETS

-0.59

POSITIVE LOGITS

 Others

1.33

 others

1.20

Others

1.17

 ones

0.78

some

0.69

mouth

0.68

 latter

0.67

Ago

0.63

 juveniles

0.61

mostly

0.61

Activations Density 0.422%

phrases indicating contrasting or differing opinions

phrases indicating contrasting opinions or evaluations

No Comments

No Known Activations