INDEX

Explanations

important changes or transitions in various metrics, such as numbers, percentages, or rankings

oai_token-act-pair · gpt-3.5-turbo

phrases related to numerical increases and changes in statistics or metrics

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ACTION

-0.73

,,,,

-0.70

»Ĵ

-0.69

ghost

-0.68

"))

-0.68

FORMATION

-0.66

edi

-0.63

PASS

-0.62

ãĤ£

-0.62

æĸ¹

-0.60

POSITIVE LOGITS

 standpoint

0.98

 onwards

0.97

 onward

0.81

 inception

0.77

govtrack

0.69

 perspective

0.68

 beginnings

0.66

 viewpoint

0.63

 confines

0.61

thumbnails

0.61

Activations Density 0.280%

important changes or transitions in various metrics, such as numbers, percentages, or rankings

phrases related to numerical increases and changes in statistics or metrics

No Comments

No Known Activations