INDEX

Explanations

phrases related to transitions or changes from one state to another

oai_token-act-pair · gpt-3.5-turbo

phrases indicating transitions or changes from one state or condition to another

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

QUI

-0.94

iosyn

-0.78

packed

-0.76

vic

-0.73

blance

-0.70

proof

-0.69

ancial

-0.68

iest

-0.67

hn

-0.67

iar

-0.66

POSITIVE LOGITS

 afar

0.99

 whence

0.87

 thence

0.78

 obscurity

0.69

 abroad

0.67

 scratch

0.66

":"/

0.64

 baseline

0.63

 indoors

0.63

 inception

0.61

Activations Density 0.088%

phrases related to transitions or changes from one state to another

phrases indicating transitions or changes from one state or condition to another

No Comments

No Known Activations