INDEX

Explanations

years or time periods from the past

oai_token-act-pair · gpt-3.5-turbo

phrases indicating specific time periods or historical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ngth

-0.77

tackle

-0.74

hyde

-0.73

omever

-0.72

BIL

-0.71

olo

-0.70

uty

-0.70

ratom

-0.70

POSE

-0.69

nav

-0.68

POSITIVE LOGITS

1.64

1.63

1.60

1.57

1.49

1.48

1.36

1.34

ixties

1.34

1.29

Activations Density 0.258%

years or time periods from the past

phrases indicating specific time periods or historical contexts

No Comments

No Known Activations