INDEX

Explanations

words related to success, progress, and achievements

oai_token-act-pair · gpt-3.5-turbo

positive descriptors related to quality and value

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

 Niet

-0.80

eur

-0.62

anwhile

-0.62

DN

-0.60

alian

-0.59

 Strauss

-0.58

Cul

-0.58

 vacated

-0.57

 Chin

-0.57

hens

-0.56

POSITIVE LOGITS

 strides

1.13

 sense

1.05

 sacrifices

0.94

 progress

0.94

 noises

0.93

 impression

0.93

 Sense

0.89

 mistakes

0.89

 noise

0.89

sense

0.87

Activations Density 0.086%

words related to success, progress, and achievements

positive descriptors related to quality and value

No Comments

No Known Activations