INDEX

Explanations

numerical data such as quantities and percentages

oai_token-act-pair · gpt-3.5-turbo

numerical changes or statistics related to growth or decline over time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

âĹ¼

-0.75

Asset

-0.69

"))

-0.67

 nonetheless

-0.66

erman

-0.65

nesota

-0.65

»Ĵ

-0.64

Lens

-0.62

edi

-0.62

æĸ¹

-0.61

POSITIVE LOGITS

 standpoint

1.06

 onwards

0.96

 perspective

0.76

 inception

0.75

 perspectives

0.72

 onward

0.71

ratch

0.70

 viewpoint

0.69

 vantage

0.69

 beginnings

0.65

Activations Density 0.333%

numerical data such as quantities and percentages

numerical changes or statistics related to growth or decline over time

No Comments

No Known Activations