INDEX

Explanations

ranges or numerical values expressed as ratios

oai_token-act-pair · gpt-3.5-turbo

phrases indicating approximate numerical ranges

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

ModLoader

-0.96

åŃĲ

-0.72

ACTED

-0.71

ById

-0.69

jay

-0.68

ãĤ´ãĥ³

-0.66

çķ

-0.65

eries

-0.63

NetMessage

-0.63

ÑĮ

-0.62

POSITIVE LOGITS

1.35

1.31

1.30

1.29

1.24

1.23

1.18

1.17

Activations Density 0.050%

ranges or numerical values expressed as ratios

phrases indicating approximate numerical ranges

No Comments

No Known Activations